Loading the registry…
Reference architecture for executing AI-agent actions through an independent authorization boundary.
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.
6 critical findings reported by cisco-skill-scanner. The composite score alone does not reflect this — read the per-scanner reports below.
github: https://github.com/decionis/agent-safe-pipeline, 50 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- agent-safe-pipeline-workspace
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
7 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
0 findings · 0.7s
v2.0.11
37 findings · 10.1s
v0.3.74
2 findings · 2.6s
v0.1.0
0 findings · 3.9s
v0.1.0
0 findings · 3.9s
v0.71.0
0 findings · 0.3s
v2.3.8
0 findings · 10.2s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 2.0s
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
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 17, 2026 | Flagged90 | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source ·n/a: not applicabletrivy: completeosv-scanner: completetrivy_image ·n/a: not applicablegovulncheck ·n/a: not applicable | completed |
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 39 findings across every scanner that examined this package. None of the 6 findings rated critical by their scanner were dismissed.
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.
18 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: AAK-MCP-018, SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE and 1 more · Files: examples/mcp-tool-gate/src/Index.ts, /repo/docs/SKILL.md, /repo/examples/shopify-refund-agent/SKILL.md and 9 more · reported by agent-audit-kit, 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.
6 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/scripts/CheckFixtureProvenance.mjs, /repo/scripts/CheckLicenses.mjs, /repo/scripts/GenerateLicenseInventory.mjs and 2 more · reported by cisco-skill-scanner
3 HIDDEN_DATA_FILE
Files: /repo/.prettierrc.json, /repo/.gitleaks.toml, /repo/.markdownlint-cli2.mjs · reported by cisco-skill-scanner
3 MANIFEST_MISSING_LICENSE
Files: /repo/SKILL.md, /repo/conformance/vectors/SKILL.md, /repo/packages/pipeline/SKILL.md · reported by cisco-skill-scanner
3 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/conformance/vectors/SKILL.md, /repo/packages/pipeline/SKILL.md · reported by cisco-skill-scanner
2 FILE_MAGIC_MISMATCH
Files: /repo/llms-full.txt, /repo/llms.txt · reported by cisco-skill-scanner
2 LOW_ANALYZABILITY
Files: /repo, /repo/packages/pipeline · reported by cisco-skill-scanner
1
Critical command injection vulnerabilities found in scripts.
The artifact contains critical command injection vulnerabilities in multiple JavaScript files, specifically within `/repo/scripts/CheckFixtureProvenance.mjs`, `/repo/scripts/CheckLicenses.mjs`, `/repo/scripts/GenerateLicenseInventory.mjs`, `/repo/scripts/PreCommit.mjs`, and `/repo/scripts/VerifyBootstrapTarball.mjs`. These findings indicate a capability for shell execution. Additionally, medium severity findings include file magic mismatches and an agent audit kit supply chain issue.
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.
Files: package.json · reported by agent-audit-kit
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner