Loading the registry…
CodeInspectus, by Synvoya — a local-first, privacy-preserving security MCP server that scans AI-generated code for real vulnerabilities, maps findings to compliance frameworks, and drives a scan → fix → rescan loop. Zero network egress at scan time.
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.
66 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 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/Synvoya/codeinspectus, 229 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- codeinspectus
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 · 2.6s
v2.0.11
147 findings · 179.7s
v0.3.26
64 findings · 68.5s
v0.1.0
18 findings · 147.9s
v0.1.0
0 findings · 148.0s
v0.1.0
0 findings · 51.1s
No report in this scan: capslock, govulncheck, osv-scanner, trivy, trivy_image.
3 scans on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 3, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
| Jul 30, 2026 | Scan Halted | — | cisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
| Jul 29, 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 229 findings across every scanner that examined this package. 63 of 66 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.
176 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, SECRET_STRIPE_KEY, COMMAND_INJECTION_JS_CHILD_PROCESS and 22 more · Files: /repo/fixtures/llm-dynamic-execution-corpus/fp/01-constants.ts, /repo/fixtures/llm-dynamic-execution-corpus/fp/04-request-not-model.ts, /repo/fixtures/llm-dynamic-execution-corpus/tp/03-child-process-exec.ts and 69 more · reported by cisco-skill-scanner, agent-audit-kit, nerlo-behavioral
19 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: YARA_indirect_prompt_injection_generic, SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE · Files: /repo/docs/THREAT-MODEL-WORKFLOW.md, /repo/docs/SKILL.md, /repo/fixtures/SKILL.md and 6 more · reported by cisco-skill-scanner
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/PULL_REQUEST_TEMPLATE/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.
7 MANIFEST_MISSING_LICENSE
Files: /repo/agent-rules/codeinspectus-multi-review/SKILL.md, /repo/agent-rules/codeinspectus-fix-one/SKILL.md, /repo/agent-rules/codeinspectus-threat-model/SKILL.md and 4 more · reported by cisco-skill-scanner
5 AAK-SECRET-004
Files: evals/run-evals.ts, src/issue-payload/test-fixture.ts, src/ai-checks/client-secrets.ts · reported by agent-audit-kit
4 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/agent-rules/SKILL.md, /repo/detection-db/osv-pub/SKILL.md and 1 more · reported by cisco-skill-scanner
2 DATA_EXFIL_JS_NETWORK
Files: /repo/src/install.ts · reported by cisco-skill-scanner
2 YARA_code_execution_generic
Files: /repo/detection-db/opengrep-rules/security-baseline/injection.yaml · reported by cisco-skill-scanner
1 AAK-ANTHROPIC-SDK-001
Files: src/server.ts · reported by agent-audit-kit
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-SEC-MD-001
Files: SECURITY.md · reported by agent-audit-kit
1 AAK-SUPPLY-005
Files: package-lock.json · reported by agent-audit-kit
1 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/src/ai-checks/unsafe-tool-execution.ts · reported by cisco-skill-scanner
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 FILE_MAGIC_MISMATCH
Files: /repo/src/ai-checks/unsafe-tool-execution.ts · reported by cisco-skill-scanner
1 HIDDEN_DATA_FILE
Files: /repo/.gitleaks.toml · reported by cisco-skill-scanner
1 LOW_ANALYZABILITY
Files: /repo · reported by cisco-skill-scanner
1 SECRET_STRIPE_KEY
Files: /repo/evals/run-evals.ts · reported by cisco-skill-scanner
1 YARA_credential_harvesting_generic
Files: /repo/scripts/redaction-e2e.mjs · reported by cisco-skill-scanner
Critical risks: command injection, credential harvesting, and exposed Stripe key.
The artifact contains code that allows command injection via child process execution in `src/ai-checks/unsafe-tool-execution.ts`. It also includes generic credential harvesting capabilities in `scripts/redaction-e2e.mjs` and an exposed Stripe key in `evals/run-evals.ts`. Additionally, multiple high-severity secrets are present across various files, including `evals/run-evals.ts`, `src/ai-checks/client-secrets.ts`, and `src/issue-payload/test-fixture.ts`.
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.