Loading the registry…
We found this by crawling public sources and nobody has attested to it. That is how most of the registry gets here, and it is not a mark against the artifact — it only means no authenticated act of publication is on record. An artifact can be the vendor's own and still appear here.
7 critical findings reported by cisco-skill-scanner, agent-audit-kit, 0 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- turul-mcp-framework
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
8 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
3 findings · 0.6s
v2.0.11
253 findings · 25.1s
v0.3.74
181 findings · 19.6s
v0.1.0
0 findings · 4.3s
v0.1.0
5 findings · 4.3s
vv0.3.2
Incomplete run
0 findings · 0.4s
v0.71.0
1 finding · 0.5s
v2.3.8
47 findings · 0.8s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 1.0s
v0.71.0
No container image was published for this artifact. What each scanner covers
0 findings · 0.0s
vv1.6.0
No Go modules were found in this artifact. What each scanner covers
0 findings · 0.1s
4 scans on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Sep 1, 2026 | Flagged74 | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·!: incompletenerlo-multi-source ·n/a: not applicabletrivy: completeosv-scanner: completetrivy_image ·n/a: not applicablegovulncheck ·n/a: not applicable | completed |
| Aug 2, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source ·n/a: not applicable | rejected |
| Jul 30, 2026 | Scan Halted | — | cisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source ·n/a: not applicable | rejected |
| Jul 28, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source ·n/a: not applicable | 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 490 findings across every scanner that examined this package. 7 of 7 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 123 findings stand exactly as their scanners reported them, at full severity, as they would have without this review.
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.
191 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: YARA_command_injection_generic, YARA_credential_harvesting_generic, AAK-MCP-DEPRECATED-003 and 5 more · Files: /repo/scripts/test_middleware_live.sh, /repo/scripts/test_rate_limit.sh, /repo/tests/roots/tests/roots_security_e2e.rs and 107 more · reported by cisco-skill-scanner, agent-audit-kit
11 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-002, AAK-AGENT-003 · Files: AGENTS.md, CLAUDE.md · reported by agent-audit-kit
9 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: AAK-TAINT-002, FILE_MAGIC_MISMATCH, HIDDEN_DATA_FILE and 1 more · Files: examples/derive-macro-server/src/main.rs, /repo/examples/derive-macro-server/data/code_templates.json, /repo/examples/lambda-mcp-server/.env and 3 more · reported by agent-audit-kit, cisco-skill-scanner, nerlo-install-instruction
2 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 · Files: .github/workflows/ci.yml · reported by agent-audit-kit
The model could have called any of these a false positive and did not.
51 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/turul-mcp-skills/skills/resource-prompt-patterns/SKILL.md, /repo/plugins/turul-mcp-skills/skills/auth-patterns/SKILL.md, /repo/plugins/turul-mcp-skills/skills/output-schemas/SKILL.md and 48 more · reported by cisco-skill-scanner
33 AAK-MCP-DEPRECATED-003
Files: crates/turul-mcp-protocol-2025-11-25/src/lib.rs, crates/turul-mcp-protocol-2025-11-25/src/prelude.rs, crates/turul-mcp-protocol-2025-11-25/src/notifications.rs and 30 more · reported by agent-audit-kit
29 AAK-MCP-DEPRECATED-001
Files: crates/turul-mcp-ext-tasks/schema/draft-schema.ts, crates/turul-mcp-protocol-2025-11-25/src/param_extraction.rs, crates/turul-mcp-protocol-2025-11-25/src/lib.rs and 26 more · reported by agent-audit-kit
26 AAK-MCP-DEPRECATED-002
Files: crates/turul-mcp-ext-tasks/schema/draft-schema.ts, crates/turul-mcp-protocol-2025-11-25/src/sampling.rs, crates/turul-mcp-protocol-2025-11-25/src/traits.rs and 23 more · reported by agent-audit-kit
6 AAK-SSRF-002
Files: tests/mcp_behavioral_compliance.rs, examples/resource-test-server/src/main.rs, examples/oauth-resource-server/src/main.rs and 3 more · reported by agent-audit-kit
4 LOW_ANALYZABILITY
Files: /repo/crates/turul-mcp-ext-apps/schema, /repo/crates/turul-mcp-protocol-2026-07-28/schema, /repo/crates/turul-mcp-ext-tasks/schema and 1 more · reported by cisco-skill-scanner
3 AAK-SECRET-004
Files: crates/turul-mcp-aws-lambda/src/adapter.rs, crates/turul-mcp-aws-lambda/src/cors.rs · reported by agent-audit-kit
1 AAK-SUPPLY-004
Files: Cargo.toml · reported by agent-audit-kit
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
100 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: AAK-MCP-ROUTING-DESYNC-001, YARA_indirect_prompt_injection_generic, AAK-HEALTHCARE-AI-004 and 54 more · Files: scripts/interop-go-sdk-probe/main.go, /repo/crates/turul-mcp-ext-apps/schema/apps-2026-01-26.mdx, CHANGELOG.md and 46 more · reported by agent-audit-kit, cisco-skill-scanner, agentshield and 3 more
23 The model gave no reason we were willing to publish, and a verdict without one is not usable evidence.
Rules: AAK-MCP-SSRF-001 · Files: tests/ping_auth_2025.rs, tests/mcp_runtime_capabilities_validation.rs, crates/turul-mcp-server/tests/progress_2026.rs and 20 more · reported by agent-audit-kit
Artifact has SSRF vulnerabilities and exposed secrets.
The artifact contains multiple high-severity Server-Side Request Forgery (SSRF) vulnerabilities in test and example code, which could lead to network egress. Additionally, high-severity findings indicate exposed secrets within `crates/turul-mcp-aws-lambda/src/adapter.rs` and `crates/turul-mcp-aws-lambda/src/cors.rs`. Several medium-severity findings also point to potential indirect prompt injection and further SSRF risks.
Concern level assessed by the review: High. 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.