Loading the registry…
Provider-agnostic coding protocols and project verification for AI agents
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. 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/johnnymaconny/mighty-mouse, 420 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- mighty-mouse
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
5 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.
v2.0.11
188 findings · 34.3s
v0.3.74
Timed out
0 findings · 450.0s
v0.1.0
3 findings · 8.5s
v0.1.0
1 finding · 8.5s
v0.1.0
0 findings · 12.8s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.2s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
No report in this scan: 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 21, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit ·!: timeoutnerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-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 192 findings across every scanner that examined this package. None of the 7 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: HIDDEN_DATA_FILE, SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE and 1 more · Files: /repo/.agents/skills/mighty-mouse/examples/basic_refactor.md, /repo/docs/SKILL.md, /repo/docs/releases/SKILL.md and 7 more · reported by cisco-skill-scanner, nerlo-install-instruction
3 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: HIDDEN_EXECUTABLE_SCRIPT, FILE_MAGIC_MISMATCH · Files: /repo/.agents/scripts/test_delivery_guard.py, /repo/tasks/fixtures/test_hygiene_fixture/fixture.py, /repo/tasks/fixtures/closeout_fixture/data_fixture.py · reported by cisco-skill-scanner
1 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: TOOL_ABUSE_UNDECLARED_NETWORK · Files: /repo/repo/AGENTS.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.
42 MANIFEST_MISSING_LICENSE
Files: /repo/skills/hermes/SKILL.md, /repo/skills/antigravity/SKILL.md, /repo/.agents/skills/validate-implementation-plan/SKILL.md and 39 more · reported by cisco-skill-scanner
36 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/skills/SKILL.md, /repo/mcp/SKILL.md and 33 more · reported by cisco-skill-scanner
28 HIDDEN_DATA_FILE
Files: /repo/.gsd/config.json, /repo/.agents/hooks.json, /repo/.agents/workflows/autoresearch-flashpoint.md and 24 more · reported by cisco-skill-scanner
15 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/eval/run_bare_baseline.py, /repo/eval/run_local_model_pilot.py, /repo/src/mighty_mouse/experiments/local_agent.py and 2 more · reported by cisco-skill-scanner
13 MANIFEST_INVALID_NAME
Files: /repo/data/evidence/real_project_trials/PORT-002/SKILL.md, /repo/data/evidence/real_project_trials/MM-004/SKILL.md, /repo/data/evidence/real_project_trials/AUDIO-001/SKILL.md and 10 more
Critical path traversal and credential network egress
Path traversal vulnerabilities are present in multiple evaluation and service files, including `/repo/eval/generate_tier_9_pack.py` and `/repo/src/mighty_mouse/services/benchmark_service.py`. The artifact also contains a hidden executable script at `/repo/.agents/scripts/delivery_guard.py` and an infinite loop in `/repo/eval/perpetual_loop.py`. Credentials may be exposed and sent over the network from client files such as `/repo/src/mighty_mouse/orchestrator/gemini_client.py` and `/repo/src/mighty_mouse/orchestrator/ollama_client.py`. Additionally, undeclared network activity is detected.
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.
12 FILE_MAGIC_MISMATCH
Files: /repo/configs/prompt_segments/constraints.txt, /repo/src/mighty_mouse/resources/configs/prompt_segments/constraints.txt, /repo/configs/flashpoint_v1.yaml and 9 more · reported by cisco-skill-scanner
7 PATH_TRAVERSAL_OPEN
Files: /repo/eval/generate_tier_9_pack.py, /repo/eval/generate_tier_pack.py, /repo/eval/mutation_engine.py and 2 more · reported by cisco-skill-scanner
6 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/src/prototype/server.js · reported by cisco-skill-scanner
3 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/src/mighty_mouse/experiments/local_agent.py, /repo/src/mighty_mouse/orchestrator/gemini_client.py, /repo/src/mighty_mouse/orchestrator/ollama_client.py · reported by nerlo-behavioral
2 EXCESSIVE_FILE_COUNT
Files: /repo/data/evidence/., /repo/. · reported by cisco-skill-scanner
2 SECRET_PASSWORD_VAR
Files: /repo/src/mighty_mouse/orchestrator/gemini_client.py · reported by cisco-skill-scanner
1 DATA_EXFIL_SOCKET_CONNECT
Files: /repo/src/mighty_mouse/services/verifiers/sandbox_wrapper.py · reported by cisco-skill-scanner
1 HIDDEN_EXECUTABLE_SCRIPT
Files: /repo/.agents/scripts/delivery_guard.py · reported by cisco-skill-scanner
1 RESOURCE_ABUSE_INFINITE_LOOP
Files: /repo/eval/perpetual_loop.py · reported by cisco-skill-scanner
1 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/src/mighty_mouse/orchestrator/repo/src/mighty_mouse/orchestrator/checklist_template.md · reported by cisco-skill-scanner