# Security Audit Report — @affset/mcp - **Report ID:** `1c5b32a8-3ba9-468d-99f0-01fa95d76214` - **Generated:** 2026-07-31T15:35:55.181963+00:00 - **Signature:** unsigned (cosign keyless signing runs in CI; Req 22.4) ## 1. Executive Summary **Badge:** Unsafe (composite) **Security score:** 93.75 | Scanner | Badge | | --- | --- | | agent-audit-kit | Caution | | agentshield | Verified | | cisco-skill-scanner | Verified | | nerlo-behavioral | Unsafe | | nerlo-install-instruction | Verified | | nerlo-multi-source | Verified | | osv-scanner | Verified | | trivy | Verified | | trivy_image | unavailable | | Severity | Findings | | --- | --- | | critical | 0 | | high | 2 | | medium | 3 | | low | 1 | | informational | 4 | @affset/mcp is NOT recommended for integration: the scan surfaced 0 critical and 2 high-severity findings. Treat the Per-Scanner Detail section as a remediation worklist and re-scan before reconsidering. ## 2. Source Provenance - **Repository:** https://github.com/affset/mcp - **Commit scanned:** `unknown` - **License:** MIT - **Maintainer:** Elusione OÜ - **Version:** 0.1.1 ## 3. Per-Scanner Detail ### agentshield (v1.4.0) — Verified / 100.0 No findings. ### cisco-skill-scanner (v2.0.11) — Verified / 91.0 - **[informational] Critically low analyzability score** — [mcp_server policy: capability-matches-purpose class; severity high -> informational] Only 18% of skill content could be analyzed. 57 of 72 files are opaque to the scanner. The safety assessment has low confidence. (/repo:None) - **[low] Hidden data file detected** — Hidden file found: .prettierrc.json. Hidden files may contain concealed configuration or data that should be reviewed. (/repo/.prettierrc.json:None) - **[informational] Vague skill description** — [mcp_server policy: capability-matches-purpose class; severity low -> informational] Skill description is too short (16 chars). Provide detailed explanation. (/repo/SKILL.md:None) - **[informational] Skill does not specify a license** — Skill manifest does not include a 'license' field. Specifying a license helps users understand usage terms. (/repo/SKILL.md:None) - **[informational] Outbound network request primitives in JavaScript/TypeScript** — [mcp_server policy: capability-matches-purpose class; severity medium -> informational] Pattern detected: fetch( (/repo/src/client.ts:108) - **[medium] CODE EXECUTION detected by YARA** — Detects dangerous code execution patterns with untrusted input in agent skills: https://ftp". const scheme = /^([a-z][a-z0-9+.-]*):\/\//i.exec(domain) (/repo/src/lib/integrationUrls.ts:70) ### agent-audit-kit (v0.3.26) — Caution / 75.0 - **[medium] Missing rate limiting on MCP endpoint** — An MCP server endpoint does not declare rate limiting. Unrestricted access allows credential stuffing and enumeration attacks. (src/server.ts:1) - **[medium] Repo depends on a third-party agent-platform SDK** — The project depends on an agent-platform SDK (context-ai, langsmith, helicone, langfuse, humanloop, MCP SDK). Informational finding so reviewers audit the vendor's OAuth-scope footprint before merging. Raised to MEDIUM because the April 19 2026 Vercel × Context.ai incident showed a single vendor compromise can turn into a production breach via transitive OAuth grants. (package.json:54) - **[high] MCP server built on the upstream SDK without STDIO sanitizer** — Repository declares a dependency on the upstream Anthropic / ModelContextProtocol SDK (Python 'mcp' / 'modelcontextprotocol', TS '@modelcontextprotocol/sdk', Java 'io.modelcontextprotocol:*', Rust 'mcp' / 'modelcontextprotocol') and exposes a STDIO transport ('StdioServerTransport', 'stdio_server', etc.) without a sanitizer on argv assembly. Anthropic declined to CVE this as working as designed — sanitization is the developer's responsibility. The OX Security disclosure on 2026-04-15 rolled up L (src/index.ts:None) ### nerlo-behavioral (v0.1.0) — Unsafe / 59.0 - **[high] opt.nerlo-rules.nerlo-js-secret-to-network-egress** — A secret / environment variable / token value flows into a network request (fetch / axios / XMLHttpRequest). This is the postmark-mcp supply-chain exfiltration shape reproduced in Node/JS: a credential read from the environment is shipped off-box. Confirm the egress is expected and the value is not being exfiltrated to an attacker-controlled host. (/repo/src/client.ts:108) ### nerlo-install-instruction (v0.1.0) — Verified / 100.0 No findings. ### nerlo-multi-source (v0.1.0) — Verified / 100.0 No findings. ### trivy (v0.71.0) — Verified / 100.0 No findings. ### osv-scanner (v2.3.8) — Verified / 100.0 No findings. ### trivy_image (v0.71.0) — unavailable / n/a No findings. ## 4. Threat Model Threat model synthesis has not yet run for this scan. This section is generated by the registry's LLM pipeline (Req 22.3) and will appear in the next regeneration of this report. ## 5. Audit Chain - **Scan job:** `78d69be8-f959-46ab-8faf-14922d2a919f` - **Completed:** 2026-07-30T13:26:32.308036+00:00 - **Scanner base image:** `us-central1-docker.pkg.dev/nerlo-vsk-prod/nerlo/scanner-base@sha256:04d4ebff19b52711a0fc06336d25964d24b9072474ff98811e5b82af008f1b8d` - **AI decision log entries:** 2 - `e73cea83-b7f4-4218-9c01-235902d177b3` - `ab81dfdc-3779-4571-a22f-b77a8be44d8c` ## 6. Appendix — Raw Scanner Output ```json [ { "scanner_name": "agentshield", "scanner_version": "1.4.0", "score": 100.0, "scanner_badge": "Verified", "findings": [], "execution_duration_seconds": 4.733731821004767, "status": "complete", "examined": null, "metadata": { "source": "npm", "source_url": "https://www.npmjs.com/package/ecc-agentshield", "install_command": "npm install -g ecc-agentshield@1.4.0", "scans_performed": [ "supply_chain" ] }, "display_score": 100.0, "display_badge": "Verified" }, { "scanner_name": "cisco-skill-scanner", "scanner_version": "2.0.11", "score": 91.0, "scanner_badge": "Verified", "findings": [ { "tool_name": "cisco-skill-scanner", "severity": "informational", "category": "policy_violation", "file_path": "/repo", "line_number": null, "rule_identifier": "LOW_ANALYZABILITY", "title": "Critically low analyzability score", "description": "[mcp_server policy: capability-matches-purpose class; severity high -> informational] Only 18% of skill content could be analyzed. 57 of 72 files are opaque to the scanner. The safety assessment has low confidence.", "remediation": "Replace opaque files (binaries, encrypted content) with inspectable source code to improve scan confidence." }, { "tool_name": "cisco-skill-scanner", "severity": "low", "category": "obfuscation", "file_path": "/repo/.prettierrc.json", "line_number": null, "rule_identifier": "HIDDEN_DATA_FILE", "title": "Hidden data file detected", "description": "Hidden file found: .prettierrc.json. Hidden files may contain concealed configuration or data that should be reviewed.", "remediation": "Move file to a visible location or document its purpose." }, { "tool_name": "cisco-skill-scanner", "severity": "informational", "category": "social_engineering", "file_path": "/repo/SKILL.md", "line_number": null, "rule_identifier": "SOCIAL_ENG_VAGUE_DESCRIPTION", "title": "Vague skill description", "description": "[mcp_server policy: capability-matches-purpose class; severity low -> informational] Skill description is too short (16 chars). Provide detailed explanation.", "remediation": "Provide a clear, detailed description of what the skill does and when to use it" }, { "tool_name": "cisco-skill-scanner", "severity": "informational", "category": "policy_violation", "file_path": "/repo/SKILL.md", "line_number": null, "rule_identifier": "MANIFEST_MISSING_LICENSE", "title": "Skill does not specify a license", "description": "Skill manifest does not include a 'license' field. Specifying a license helps users understand usage terms.", "remediation": "Add 'license' field to SKILL.md frontmatter (e.g., MIT, Apache-2.0)" }, { "tool_name": "cisco-skill-scanner", "severity": "informational", "category": "data_exfiltration", "file_path": "/repo/src/client.ts", "line_number": 108, "rule_identifier": "DATA_EXFIL_JS_NETWORK", "title": "Outbound network request primitives in JavaScript/TypeScript", "description": "[mcp_server policy: capability-matches-purpose class; severity medium -> informational] Pattern detected: fetch(", "remediation": "Ensure network operations are necessary and document allowed destinations" }, { "tool_name": "cisco-skill-scanner", "severity": "medium", "category": "command_injection", "file_path": "/repo/src/lib/integrationUrls.ts", "line_number": 70, "rule_identifier": "YARA_code_execution_generic", "title": "CODE EXECUTION detected by YARA", "description": "Detects dangerous code execution patterns with untrusted input in agent skills: https://ftp\".\n const scheme = /^([a-z][a-z0-9+.-]*):\\/\\//i.exec(domain)", "remediation": "Review and remove code execution pattern" } ], "execution_duration_seconds": 38.357415909005795, "status": "complete", "examined": { "unit": "skills", "count": 1 }, "metadata": { "source": "pypi", "source_url": "https://pypi.org/project/cisco-ai-skill-scanner/2.0.11/", "report_type": "cisco-skill-sast", "analyzers_used": [ "bytecode", "pipeline", "static_analyzer" ], "skills_scanned": [ "repo" ], "install_command": "pip install --require-hashes -r docker/scanner-base/cisco-skill-scanner/requirements.txt", "severity_counts": { "low": 1, "high": 0, "medium": 1, "critical": 0, "informational": 4 }, "artifact_type_policy": "mcp_server", "downweighted_findings": 3 }, "display_score": 91.0, "display_badge": "Verified" }, { "scanner_name": "agent-audit-kit", "scanner_version": "0.3.26", "score": 75.0, "scanner_badge": "Caution", "findings": [ { "tool_name": "agent-audit-kit", "severity": "medium", "category": "mcp-config", "file_path": "src/server.ts", "line_number": 1, "rule_identifier": "AAK-MCP-018", "title": "Missing rate limiting on MCP endpoint", "description": "An MCP server endpoint does not declare rate limiting. Unrestricted access allows credential stuffing and enumeration attacks.", "remediation": "Add per-IP and per-token rate limits. Reject bursts above the limit with 429." }, { "tool_name": "agent-audit-kit", "severity": "medium", "category": "supply-chain", "file_path": "package.json", "line_number": 54, "rule_identifier": "AAK-OAUTH-3P-001", "title": "Repo depends on a third-party agent-platform SDK", "description": "The project depends on an agent-platform SDK (context-ai, langsmith, helicone, langfuse, humanloop, MCP SDK). Informational finding so reviewers audit the vendor's OAuth-scope footprint before merging. Raised to MEDIUM because the April 19 2026 Vercel \u00d7 Context.ai incident showed a single vendor compromise can turn into a production breach via transitive OAuth grants.", "remediation": "Pin the SDK to an exact version, audit the OAuth scopes it requests, and keep any deployment-level grants (Vercel, GCP, Workspace) in a secrets vault \u2014 never in a committed env file. See Vercel's bulletin for sensitive-env-var guidance: https://vercel.com/kb/bulletin/vercel-april-2026-security-incident" }, { "tool_name": "agent-audit-kit", "severity": "high", "category": "supply-chain", "file_path": "src/index.ts", "line_number": null, "rule_identifier": "AAK-ANTHROPIC-SDK-001", "title": "MCP server built on the upstream SDK without STDIO sanitizer", "description": "Repository declares a dependency on the upstream Anthropic / ModelContextProtocol SDK (Python `mcp` / `modelcontextprotocol`, TS `@modelcontextprotocol/sdk`, Java `io.modelcontextprotocol:*`, Rust `mcp` / `modelcontextprotocol`) and exposes a STDIO transport (`StdioServerTransport`, `stdio_server`, etc.) without a sanitizer on argv assembly. Anthropic declined to CVE this as working as designed \u2014 sanitization is the developer's responsibility. The OX Security disclosure on 2026-04-15 rolled up L", "remediation": "Wrap every argv the STDIO transport builds in an allow-list sanitizer \u2014 `shlex.quote` in Python, `execFile` with an explicit argv array in Node, equivalent in Java/Rust. OR switch the transport off STDIO (`transports=['http']` / `['sse']`). If you have deliberately accepted the risk, add `accepts_stdio_risk: true` plus a `justification:` field in `.agent-audit-kit.yml`." } ], "execution_duration_seconds": 10.504058021993842, "status": "complete", "examined": { "unit": "files", "count": 70 }, "metadata": { "source": "pypi", "source_url": "https://pypi.org/project/agent-audit-kit/0.3.26/", "report_type": "agent-audit-kit-sast", "install_command": "pip install --require-hashes -r docker/scanner-base/agent-audit-kit/requirements.txt", "rules_evaluated": 211, "severity_counts": { "low": 0, "high": 1, "medium": 2, "critical": 0, "informational": 0 } }, "display_score": 75.0, "display_badge": "Caution" }, { "scanner_name": "nerlo-behavioral", "scanner_version": "0.1.0", "score": 59.0, "scanner_badge": "Unsafe", "findings": [ { "tool_name": "nerlo-behavioral", "severity": "high", "category": "data-exfiltration", "file_path": "/repo/src/client.ts", "line_number": 108, "rule_identifier": "opt.nerlo-rules.nerlo-js-secret-to-network-egress", "title": "opt.nerlo-rules.nerlo-js-secret-to-network-egress", "description": "A secret / environment variable / token value flows into a network request (fetch / axios / XMLHttpRequest). This is the postmark-mcp supply-chain exfiltration shape reproduced in Node/JS: a credential read from the environment is shipped off-box. Confirm the egress is expected and the value is not being exfiltrated to an attacker-controlled host.", "remediation": null } ], "execution_duration_seconds": 49.55742313398514, "status": "complete", "examined": { "unit": "files", "count": 57 }, "metadata": { "source": "nerlo-original", "source_url": "https://github.com/nerlo-ai/nerlo", "report_type": "nerlo-behavioral", "ruleset_path": "/opt/nerlo-rules/exfiltration.yaml", "ruleset_paths": [ "/opt/nerlo-rules/exfiltration.yaml", "/opt/nerlo-rules/clipboard_exfiltration.yaml", "/opt/nerlo-rules/rce_endpoint.yaml", "/opt/nerlo-rules/taint_egress.yaml" ], "install_command": "pip install 'semgrep==1.97.0'", "severity_counts": { "low": 0, "high": 1, "medium": 0, "critical": 0, "informational": 0 }, "merged_invocation": true }, "display_score": 59.0, "display_badge": "Unsafe" }, { "scanner_name": "nerlo-install-instruction", "scanner_version": "0.1.0", "score": 100.0, "scanner_badge": "Verified", "findings": [], "execution_duration_seconds": 49.56191410304746, "status": "complete", "examined": { "unit": "files", "count": 4 }, "metadata": { "source": "nerlo-original", "source_url": "https://github.com/nerlo-ai/nerlo", "report_type": "nerlo-install-instruction", "ruleset_path": "/opt/nerlo-rules/install_instructions.yaml", "ruleset_paths": [ "/opt/nerlo-rules/install_instructions.yaml", "/opt/nerlo-rules/cursor_rules.yaml" ], "install_command": "pip install 'semgrep==1.97.0'", "merged_invocation": true }, "display_score": 100.0, "display_badge": "Verified" }, { "scanner_name": "nerlo-multi-source", "scanner_version": "0.1.0", "score": 100.0, "scanner_badge": "Verified", "findings": [], "execution_duration_seconds": 29.19295543298358, "status": "complete", "examined": null, "metadata": { "source": "nerlo-original", "per_source": [ { "badge": "Verified", "label": "npm@0.1.1", "score": 100.0, "version": "0.1.1", "identifier": "@affset/mcp", "provenance": "clean", "source_type": "npm", "artifact_type": "mcp_server", "finding_count": 0, "malware_status": "complete", "injected_rule_ids": [] } ], "report_type": "nerlo-multi-source", "diverged_sources": [], "published_surfaces_scanned": 1 }, "display_score": 100.0, "display_badge": "Verified" }, { "scanner_name": "trivy", "scanner_version": "0.71.0", "score": 100.0, "scanner_badge": "Verified", "findings": [], "execution_duration_seconds": 0.9783568949787878, "status": "complete", "examined": { "unit": "manifests", "count": 1 }, "metadata": { "source": "github-releases", "source_url": "https://github.com/aquasecurity/trivy/releases/tag/v0.71.0", "report_type": "filesystem-vulnerability", "install_command": "curl -sfL -o /tmp/trivy.deb https://github.com/aquasecurity/trivy/releases/download/v0.71.0/trivy_0.71.0_Linux-64bit.deb && echo ' /tmp/trivy.deb' | sha256sum -c - && dpkg -i /tmp/trivy.deb", "manifests_scanned": [ "package-lock.json" ] }, "display_score": 100.0, "display_badge": "Verified" }, { "scanner_name": "osv-scanner", "scanner_version": "2.3.8", "score": 100.0, "scanner_badge": "Verified", "findings": [], "execution_duration_seconds": 22.769380967016332, "status": "complete", "examined": null, "metadata": { "source": "github-releases", "source_url": "https://github.com/google/osv-scanner/releases/tag/v2.3.8", "report_type": "osv-vulnerability", "ecosystems_seen": [], "install_command": "curl -sfL -o /usr/local/bin/osv-scanner https://github.com/google/osv-scanner/releases/download/v2.3.8/osv-scanner_linux_amd64 && echo ' /usr/local/bin/osv-scanner' | sha256sum -c - && chmod +x /usr/local/bin/osv-scanner", "manifests_scanned": [], "finding_id_aliases": {}, "cross_scanner_correlation": { "only_osv": [], "only_trivy": [], "intersection_ids": [] } }, "display_score": 100.0, "display_badge": "Verified" }, { "scanner_name": "trivy_image", "scanner_version": "0.71.0", "score": 100.0, "scanner_badge": "Verified", "findings": [], "execution_duration_seconds": 4.658999387174845e-05, "status": "not_applicable", "examined": { "unit": "image_targets", "count": 0 }, "metadata": { "reason": "no OCI image acquired for this artifact" }, "display_score": null, "display_badge": "unavailable" } ] ```