Loading the registry…
Local change evidence, impact review, and verification receipts for developers, CI, and coding agents.
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.
234 critical findings reported by cisco-skill-scanner, agent-audit-kit, 15 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
This artifact ships from 2 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/mirnoorata/codexa, 815 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- @mirnoorata/codexa
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
0 findings · 0.5s
v2.0.11
454 findings · 23.7s
v0.3.26
82 findings · 12.0s
v0.1.0
2 findings · 39.0s
v0.1.0
0 findings · 39.0s
v0.1.0
0 findings · 26.9s
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 4, 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 538 findings across every scanner that examined this package. 219 of 234 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.
245 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, YARA_command_injection_generic, AAK-DNS-REBIND-001 and 7 more · Files: /repo/tests/agent-ab-report.test.ts, /repo/tests/agent-ab-runner.test.ts, /repo/tests/agent-ab-v2-identity.test.ts and 35 more · reported by cisco-skill-scanner, agent-audit-kit
117 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, SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE and 1 more · Files: AGENTS.md, /repo/docs/SKILL.md, /repo/.github/SKILL.md and 41 more · reported by agent-audit-kit, cisco-skill-scanner
34 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: LOW_ANALYZABILITY, AAK-HEALTHCARE-AI-005, AAK-HEALTHCARE-AI-004 and 1 more · Files: /repo/docs/pr-summaries/codex-general-codexa-20260622-144621-focus-orientation, /repo/docs/pr-summaries/codex-general-codexa-codexa-scip-importer-20260617, /repo/docs/pr-summaries/codex-general-codexa-20260722-210037-focus-orientation and 24 more · reported by cisco-skill-scanner, agent-audit-kit
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.
71 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/scripts/prepare-codera-parking-package.mjs, /repo/scripts/verify-source-hygiene.mjs, /repo/src/autonomy.ts and 28 more · reported by cisco-skill-scanner
12 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/integrations/claude-code/scripts/codexa-mcp.js, /repo/plugins/codexa/scripts/codexa-mcp.js, /repo/scripts/benchmark-hot-paths.mjs and 2 more · reported by cisco-skill-scanner
12 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/codexa/skills/codexa/SKILL.md, /repo/SKILL.md, /repo/benchmarks/agent-ab/SKILL.md and 9 more · reported by cisco-skill-scanner
10 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/benchmarks/agent-ab/SKILL.md, /repo/benchmarks/agent-ab-selective-v2/SKILL.md and 7 more · reported by cisco-skill-scanner
6 AAK-ANTHROPIC-SDK-001
Files: scripts/package-install-smoke.mjs, scripts/benchmark-hot-paths.mjs, scripts/benchmark-mcp-transport.mjs and 3 more
Critical command injection and data exfiltration risks
The artifact includes critical command injection vulnerabilities in multiple scripts, allowing shell execution. It also has critical DNS rebind and taint vulnerabilities in core modules. Additionally, there are numerous high-severity findings related to file system access and potential data exfiltration across various 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.
5 AAK-HEALTHCARE-AI-004
Files: README.md, CODE_OF_CONDUCT.md, reports/benchmarks/v0.14.0-usefulness-baseline.json and 2 more · reported by agent-audit-kit
5 AAK-MCP-018
Files: src/mcp.ts, src/mcp/runtime.ts, src/mcp/tools.ts and 2 more · reported by agent-audit-kit
5 AAK-SECRET-004
Files: src/symbol-report-ingest.ts, src/autoverify.ts, src/parser/routes.ts and 2 more · reported by agent-audit-kit
3 HIDDEN_DATA_FILE
Files: /repo/plugins/codexa/.codex-plugin/plugin.json, /repo/.agents/plugins/marketplace.json, /repo/.release-please-manifest.json · reported by cisco-skill-scanner
2 AAK-MARKETPLACE-001
Files: .agents/plugins/marketplace.json, integrations/.claude-plugin/marketplace.json · reported by agent-audit-kit
2 DATA_EXFIL_JS_NETWORK
Files: /repo/src/eval/historical.ts, /repo/src/semantic-retrieval.ts · reported by cisco-skill-scanner
1 AAK-DNS-REBIND-001
Files: src/mcp.ts · reported by agent-audit-kit
1 AAK-OAUTH-3P-001
Files: package.json · reported by agent-audit-kit
1 AAK-SUPPLY-005
Files: package-lock.json · reported by agent-audit-kit
1 AAK-TAINT-001
Files: src/doctor.ts · reported by agent-audit-kit
1 COMMAND_INJECTION_EVAL
Files: /repo/src/query/verification/command-scope.ts · reported by cisco-skill-scanner
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 LOW_ANALYZABILITY
Files: /repo · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-hardcoded-external-egress
Files: /repo/src/semantic-retrieval.ts · reported by nerlo-behavioral
1 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/src/semantic-retrieval.ts · reported by nerlo-behavioral
Showing 25 of 101; the rest are in the per-scanner reports above.