The publisher performed an authenticated act of publication — proving control of a namespace in the official MCP registry, or appearing in a first-party catalogue an operator curates. That establishes WHO published it. It is not a security finding, and attested artifacts carry Flagged verdicts too.
83 critical findings reported by cisco-skill-scanner, agent-audit-kit, 12 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
This artifact ships from 3 sources and their verdicts differ. The worst is github (Flagged). Installing from a cleaner source does not mean the others are safe — check the source you actually install from. Some sources have no verdict at all; that is not a pass.
github: https://github.com/superserve-ai/superserve, 286 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- superserve
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
6 of 11 scanners examined this package. The rest do not apply to it — language, ecosystem and packaging decide which analyzers can say anything, and a scanner that cannot examine an artifact reports nothing rather than passing it.
v1.4.0
5 findings · 2.8s
v2.0.11
131 findings · 84.2s
v0.3.26
119 findings · 45.3s
v0.1.0
12 findings · 106.0s
v0.1.0
19 findings · 106.0s
v0.1.0
0 findings · 45.0s
No report in this scan: capslock, govulncheck, osv-scanner, trivy, trivy_image.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 2, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
Findings in files this artifact installs stand as reported; a model re-read the rest and said which ones it believes are false positives. This is a second opinion published beside the evidence, not a correction to it: the per-scanner reports above are unchanged, every dismissed finding is still listed there at its original severity, and the score and the Flagged badge are computed from those raw severities alone. Nothing below moved them.
Out of 286 findings across every scanner that examined this package. 67 of 83 findings rated critical by their scanner were among the dismissals.
Two keys had to turn. The model had to name a reason from a fixed list of six, and a deterministic check of ours — over which files this artifact actually installs — had to independently agree. Anything it could not corroborate is in “not reviewed” above, at full severity.
63 Agent instruction file — The match is in a file that instructs an AI coding agent — a CLAUDE.md or similar. It is documentation of intent, and our own check confirmed it is not part of what gets installed.
Rules: AAK-AGENT-001, AAK-AGENT-003, secrets-claude-md-env-1201 and 1 more · Files: CLAUDE.md, /repo/repo/CLAUDE.md · reported by agent-audit-kit, agentshield, cisco-skill-scanner
36 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: opt.nerlo-rules.nerlo-install-pipe-to-shell, PIPELINE_TAINT_FLOW, opt.nerlo-rules.nerlo-install-run-bundled-artifact and 3 more · Files: /repo/docs/integrations/coding-agents/opencode.mdx, /repo/docs/storage/archil.mdx, /repo/docs/storage/mesa.mdx and 11 more · reported by nerlo-install-instruction, cisco-skill-scanner
14 Test or fixture file — The match is in a test or fixture. Our own check confirmed the file is not part of what gets installed.
Rules: COMMAND_INJECTION_EVAL, AAK-SECRET-001, YARA_command_injection_generic and 4 more · Files: /repo/packages/mcp/tests/e2e.test.ts, /repo/packages/mcp/tests/fake-client.ts, examples/loops/tests/install.test.ts and 6 more · reported by cisco-skill-scanner, agent-audit-kit
11 CI or editor configuration — The match is in build, CI or editor configuration, confirmed by our own check to be outside the installed artifact.
Rules: AAK-GHA-IMMUTABLE-001, permissions-no-block, hooks-no-pretooluse and 1 more · Files: .github/workflows/ci.yml, .github/workflows/cli-publish.yml, .github/workflows/mcp-publish.yml and 5 more · reported by agent-audit-kit, agentshield, cisco-skill-scanner
These findings are in files this artifact installs and are not placeholder values. No false-positive basis can be corroborated for such a finding, so this review never dismisses one; they were not sent to the model and stand at their scanner's severity.
25 DATA_EXFIL_JS_NETWORK
Files: /repo/apps/console/src/app/(public)/device/page.tsx, /repo/apps/console/src/app/api/[...path]/route.ts, /repo/apps/console/src/app/api/team-management/[[...path]]/route.ts and 7 more · reported by cisco-skill-scanner
17 AAK-SECRET-004
Files: packages/python-sdk/src/superserve/_config.py, packages/sdk/src/config.ts, apps/console/src/lib/posthog/actions.ts and 14 more · reported by agent-audit-kit
12 AAK-LEGAL-002
Files: package.json, packages/ui/package.json, packages/typescript-config/package.json and 9 more · reported by agent-audit-kit
11 MANIFEST_MISSING_LICENSE
Files: /repo/skills/superserve/SKILL.md, /repo/SKILL.md, /repo/packages/cli/SKILL.md and 8 more · reported by cisco-skill-scanner
10 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/packages/cli/SKILL.md, /repo/packages/mcp/SKILL.md and 7 more · reported by cisco-skill-scanner
The model could have called any of these a false positive and did not.
4 YARA_tool_chaining_abuse_generic
Files: /repo/examples/loops/pr-loop/skill/SKILL.md · reported by cisco-skill-scanner
3 AAK-LEGAL-002
Files: examples/loops/package.json, tests/sdk-e2e-ts/package.json, tests/sdk-e2e-py/package.json · reported by agent-audit-kit
3 AAK-SECRET-004
Files: docs/docs.json, tests/sdk-e2e-ts/scripts/test-template.ts · reported by agent-audit-kit
3 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/examples/loops/e2e/scenario.ts · reported by cisco-skill-scanner
2 PROMPT_INJECTION_IGNORE_INSTRUCTIONS
Files: /repo/examples/loops/pr-loop/skill/SKILL.md · reported by cisco-skill-scanner
1 AAK-HEALTHCARE-AI-004
Files: examples/loops/pr-loop/README.md · reported by agent-audit-kit
Artifact has critical command injection and credential exposure risks.
The artifact contains multiple instances of command injection via child processes and `eval` in files such as `/repo/packages/mcp/src/client.ts` and `/repo/packages/cli/src/utils/python-deps.ts`, which could lead to shell execution. It also exposes credentials in various files, including `apps/console/src/lib/posthog/actions.ts` and several Python guides. Additionally, there is potential for network egress of secrets and clipboard data exfiltration.
Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.
Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.
9 LOW_ANALYZABILITY
Files: /repo/guides/managed-agents/claude-managed-agents/recipes/parallel-benchmark-agent, /repo/guides/managed-agents/claude-managed-agents/recipes/research-agent, /repo/guides/managed-agents/claude-managed-agents/recipes/dev-environment and 6 more · reported by cisco-skill-scanner
8 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/apps/console/src/app/(public)/device/page.tsx, /repo/apps/console/src/components/sandboxes/terminal.tsx, /repo/apps/console/src/lib/api/files.ts and 3 more · reported by nerlo-behavioral
8 RESOURCE_ABUSE_INFINITE_LOOP
Files: /repo/packages/python-sdk/src/superserve/async_template.py, /repo/packages/python-sdk/src/superserve/template.py · reported by cisco-skill-scanner
8 SECRET_PASSWORD_VAR
Files: /repo/apps/console/src/app/(auth)/auth/reset-password/page.tsx, /repo/apps/console/src/app/(auth)/auth/signup/page.tsx · reported by cisco-skill-scanner
4 COMMAND_INJECTION_EVAL
Files: /repo/packages/mcp/src/client.ts · reported by cisco-skill-scanner
4 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/packages/cli/scripts/build.ts, /repo/packages/cli/src/utils/python-deps.ts · reported by cisco-skill-scanner
4 HIDDEN_DATA_FILE
Files: /repo/.oxfmtrc.json, /repo/.pre-commit-config.yaml, /repo/.oxlintrc.json and 1 more · reported by cisco-skill-scanner
4 opt.nerlo-rules.nerlo-clipboard-read-exfiltration
Files: /repo/guides/managed-agents/claude-managed-agents/recipes/dev-environment/typescript/orchestrator.mjs, /repo/guides/managed-agents/claude-managed-agents/recipes/parallel-benchmark-agent/typescript/orchestrator.mjs, /repo/guides/managed-agents/claude-managed-agents/recipes/research-agent/typescript/orchestrator.mjs and 1 more · reported by nerlo-behavioral
3 AAK-MCP-018
Files: packages/mcp/src/httpServer.ts, packages/mcp/src/index.ts, packages/mcp/src/lib/sdk.ts · reported by agent-audit-kit
2 AAK-TAINT-001
Files: packages/mcp/src/lib/httpAuth.ts, packages/mcp/src/tools/exec.ts · reported by agent-audit-kit
2 COMMAND_INJECTION_JS_FUNCTION_CONSTRUCTOR
Files: /repo/apps/console/src/components/sandboxes/create-sandbox-dialog.tsx · reported by cisco-skill-scanner
2 EXCESSIVE_FILE_COUNT
Files: /repo/., /repo/apps/console/. · reported by cisco-skill-scanner
2 FILE_MAGIC_MISMATCH
Files: /repo/packages/cli/bunfig.toml · reported by cisco-skill-scanner
1 AAK-MCPFRAME-001
Files: guides/managed-agents/claude-managed-agents/typescript/orchestrator-webhook.mjs · reported by agent-audit-kit
1 AAK-SKILL-003
Files: skills/superserve/SKILL.md · reported by agent-audit-kit
1 AAK-SUPPLY-003
Files: package.json · reported by agent-audit-kit
1 AAK-SUPPLY-004
Files: package.json · reported by agent-audit-kit
1 AAK-TAINT-003
Files: packages/mcp/src/tools/files.ts · reported by agent-audit-kit
1 hooks-no-pretooluse
Files: .zed/settings.json · reported by agentshield
1 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/packages/cli/install.sh · reported by nerlo-install-instruction
1 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/skills/superserve/SKILL.md · reported by nerlo-install-instruction
1 permissions-no-block
Files: .zed/settings.json · reported by agentshield
1 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/packages/python-sdk/repo/packages/python-sdk/README.md · reported by cisco-skill-scanner
1 HIDDEN_DATA_FILE
Files: /repo/.env.release.example · reported by cisco-skill-scanner
Showing 25 of 60; the rest are in the per-scanner reports above.