Loading the registry…
Automatic Codex plan review in Claude Code; on-demand in local MCP hosts; human approval stays yours
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.
143 critical findings reported by cisco-skill-scanner, agent-audit-kit, 3 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.
github: https://github.com/yannmenec/inspectrum, 214 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- inspectrum
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
11 findings · 3.2s
v2.0.11
45 findings · 58.2s
v0.3.26
154 findings · 18.6s
v0.1.0
0 findings · 51.2s
v0.1.0
0 findings · 51.2s
v0.1.0
0 findings · 31.3s
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 210 findings across every scanner that examined this package. 140 of 143 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 4 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.
140 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, AAK-HEALTHCARE-AI-004 and 1 more · Files: AGENTS.md, CLAUDE.md · reported by agent-audit-kit, agentshield
21 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-005, SOCIAL_ENG_VAGUE_DESCRIPTION, skills-missing-governance-examples/claude-code/.claude/commands/review-plan.md and 3 more · Files: examples/claude-code/mcp.json, examples/cursor/.cursor/mcp.json, /repo/docs/SKILL.md and 8 more · reported by agent-audit-kit, cisco-skill-scanner, agentshield
9 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_JS_CHILD_PROCESS, DATA_EXFIL_JS_FS_ACCESS, AAK-SECRET-004 and 2 more · Files: /repo/tests/contract/plan-gate-cli.contract.test.ts, /repo/tests/contract/plan-gate-shim.contract.test.ts, /repo/tests/unit/session/store.test.ts and 3 more · reported by cisco-skill-scanner, agent-audit-kit
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: MANIFEST_INVALID_NAME · Files: /repo/.github/ISSUE_TEMPLATE/SKILL.md, /repo/.github/SKILL.md · reported by 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.
5 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/inspectrum/skills/review-plan-with-claude/SKILL.md, /repo/SKILL.md, /repo/commands/SKILL.md and 2 more · reported by cisco-skill-scanner
3 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/scripts/build-mcpb.mjs, /repo/scripts/verify-mcpb.mjs, /repo/src/reviewers/health.ts · reported by cisco-skill-scanner
3 DATA_EXFIL_JS_NETWORK
Files: /repo/scripts/check-submission-readiness.mjs, /repo/src/reviewers/common.ts, /repo/src/reviewers/health.ts · reported by cisco-skill-scanner
3 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/_decisions/SKILL.md, /repo/assets/brand/SKILL.md · reported by cisco-skill-scanner
2 AAK-ANTHROPIC-SDK-001
Files: scripts/verify-mcpb.mjs, src/server.ts · reported by agent-audit-kit
2
2 The model did not answer for these findings.
Rules: mcp-npx-y-inspectrum · Files: examples/claude-code/mcp.json, examples/cursor/.cursor/mcp.json · reported by agentshield
2 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: skills-missing-telemetry-commands/review.md, skills-missing-governance-commands/review.md · Files: commands/review.md · reported by agentshield
Artifact allows shell execution and sensitive data access.
The artifact contains critical command injection vulnerabilities in scripts that could lead to shell execution. It also has high-severity findings related to file system access, potentially allowing sensitive data exfiltration. Further, the artifact includes high-severity findings concerning the use of an Anthropic SDK and marketplace integration, alongside medium-severity network egress capabilities. These issues are present in various scripts and configuration files.
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: .claude-plugin/marketplace.json, .agents/plugins/marketplace.json · reported by agent-audit-kit
2 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/src/config.ts, /repo/src/doctor.ts · reported by cisco-skill-scanner
2 HIDDEN_DATA_FILE
Files: /repo/.agents/plugins/marketplace.json, /repo/plugins/inspectrum/.codex-plugin/plugin.json · reported by cisco-skill-scanner
1 AAK-MCP-018
Files: src/server.ts · reported by agent-audit-kit
1 AAK-OAUTH-3P-001
Files: package.json · reported by agent-audit-kit
1 AAK-STATE-PRIVACY-001
Files: PRIVACY.md · reported by agent-audit-kit
1 AAK-STATE-PRIVACY-002
Files: PRIVACY.md · reported by agent-audit-kit
1 AAK-STATE-PRIVACY-003
Files: PRIVACY.md · reported by agent-audit-kit
1 AAK-SUPPLY-005
Files: package-lock.json · reported by agent-audit-kit
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 FILE_MAGIC_MISMATCH
Files: /repo/eslint.config.js · reported by cisco-skill-scanner
1 hooks-logging-disabled-2326
Files: scripts/plan-gate-shim.sh · reported by agentshield
1 hooks-no-stop-hooks
Files: hooks/hooks.json · reported by agentshield
1 LOW_ANALYZABILITY
Files: /repo · reported by cisco-skill-scanner
1 MANIFEST_INVALID_NAME
Files: /repo/_decisions/SKILL.md · reported by cisco-skill-scanner