Loading the registry…
Cursor Rules are .cursorrules / .cursor/rules files that steer Cursor's AI; scanned with the same pipeline.
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.
66 critical findings reported by cisco-skill-scanner, 2 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
Cursor Rules are .cursorrules / .cursor/rules files that steer Cursor's AI. Review the scanned source before copying them into your own project.
nerlo install -- cmw-rag
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.
v1.4.0
0 findings · 0.6s
v2.0.11
625 findings · 79.7s
v0.3.74
26 findings · 53.6s
v0.1.0
8 findings · 16.7s
v0.1.0
5 findings · 16.8s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.2s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 1.3s
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: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source ·n/a: not applicable | 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 664 findings across every scanner that examined this package. 64 of 66 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 2 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.
188 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, AAK-SECRET-004, DATA_EXFIL_NETWORK_REQUESTS and 5 more · Files: /repo/docs/analysis/experiments/2026-02-19-backend-inference-tests/test-scripts/test_comprehensive_all_models.py, /repo/docs/analysis/experiments/2026-02-19-backend-inference-tests/test-scripts/test_direct_embeddings.py, /repo/docs/analysis/experiments/2026-02-19-backend-inference-tests/test-scripts/test_final_comparison_2026-02-20.py and 27 more · reported by cisco-skill-scanner, agent-audit-kit
140 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: FILE_MAGIC_MISMATCH, UNANALYZABLE_BINARY, LOW_ANALYZABILITY and 7 more · Files: /repo/docs/research/executive-research-technology-transfer/deep-researches/cmo_followup.md, /repo/docs/research/executive-research-technology-transfer/deep-researches/llm_economics.md, /repo/docs/research/executive-research-technology-transfer/deep-researches/cmo_survey.md and 57 more · reported by cisco-skill-scanner, agent-audit-kit
10 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-002, TOOL_ABUSE_UNDECLARED_NETWORK · Files: AGENTS.md, /repo/repo/AGENTS.md, /repo/docs/repo/docs/ASYNC_IMPLEMENTATION_SUMMARY.md and 3 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.
134 HIDDEN_DATA_FILE
Files: /repo/.opencode/plans/20260331-research-pack-master-action-plan.md, /repo/.opencode/plans/20260329-appendix-d-enhancement-synthesis.md, /repo/.opencode/plans/20260410-sizing-economics-step7-restoration.md and 130 more · reported by cisco-skill-scanner
40 FILE_MAGIC_MISMATCH
Files: /repo/.opencode/plans/2026-04-07-report-pack-cleanup/PATCH-01-intro-ru.md, /repo/.opencode/plans/2026-04-07-report-pack-cleanup/PATCH-10-appendix-f-extended-reading-ru.md, /repo/.opencode/plans/2026-04-07-report-pack-cleanup/PATCH-09-appendix-e-market-technical-signals-ru.md and 7 more · reported by cisco-skill-scanner
31 MANIFEST_MISSING_LICENSE
Files: /repo/.agents/skills/kb-widget-dev/SKILL.md, /repo/.agents/skills/cmw-rag-corpus-sync/SKILL.md, /repo/SKILL.md and 28 more · reported by cisco-skill-scanner
30 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/.agents/skills/kb-widget-dev/SKILL.md, /repo/SKILL.md, /repo/.cursor/SKILL.md and 27 more · reported by cisco-skill-scanner
28 DATA_EXFIL_NETWORK_REQUESTS
2 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: HIDDEN_DATA_FILE · Files: /repo/.env-example, /repo/.opencode/research/20260610_ai-chat-widget-ui/20_examples.md · reported by cisco-skill-scanner
Critical command injection and credential access risks
The artifact contains critical command injection vulnerabilities in `/repo/rag_engine/retrieval/embedder.py` and `/repo/rag_engine/api/app.py`, allowing for arbitrary code execution. It also has multiple instances of shell execution with potential command injection in `/repo/rag_engine/scripts/show_agent_load.py`. Furthermore, there are high-severity findings for credential access in `rag_engine/scripts/reranker_benchmark_from_dataset.py` and potential secret exfiltration via network egress across several scripts.
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.
22 MANIFEST_INVALID_NAME
Files: /repo/.opencode/research/20260604_mkdocs_corpus_sync/SKILL.md, /repo/.opencode/plans/20260604_mkdocs_corpus_sync/SKILL.md, /repo/.opencode/research/20260604_versioned_retrieval/SKILL.md and 19 more · reported by cisco-skill-scanner
12 COMMAND_INJECTION_SHELL_TRUE
Files: /repo/rag_engine/scripts/show_agent_load.py · reported by cisco-skill-scanner
8 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/rag_engine/scripts/extend_dataset_and_benchmark.py, /repo/rag_engine/scripts/investigate_embed_rerank_instructions.py, /repo/rag_engine/scripts/openrouter_langchain_usage_probe.py and 5 more · reported by nerlo-behavioral
4 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/.cursor/plans/async_chroma_retriever_f90a0838.plan.md, /repo/.opencode/plans/20260420_read_file_tool/plan.md · reported by nerlo-install-instruction
3 EXCESSIVE_FILE_COUNT
Files: /repo/., /repo/.opencode/plans/., /repo/.opencode/. · reported by cisco-skill-scanner
1 AAK-HEALTHCARE-AI-004
Files: .opencode/plans/20260227-anonymization-implementation-plan.md · reported by agent-audit-kit
1 AAK-LEGAL-002
Files: package.json · reported by agent-audit-kit
1 AAK-SECRET-004
Files: rag_engine/scripts/reranker_benchmark_from_dataset.py · reported by agent-audit-kit
1 AAK-SKILL-UNTRUSTED-EXEC-PATH
Files: rag_engine/scripts/show_agent_load.py · reported by agent-audit-kit
1 AAK-SPLUNK-TOKLOG-001
Files: rag_engine/llm/llm_manager.py · reported by agent-audit-kit
1 AAK-SUPPLY-004
Files: pyproject.toml · reported by agent-audit-kit
1 BINARY_FILE_DETECTED
Files: /repo/rag_engine/requirements_frozen.txt · reported by cisco-skill-scanner
1 COMMAND_INJECTION_EVAL
Files: /repo/rag_engine/retrieval/embedder.py · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-install-shell-inline-command
Files: /repo/.agents/skills/kb-widget-dev/SKILL.md · reported by nerlo-install-instruction
1 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/rag_engine/scripts/repo/rag_engine/scripts/cursor_ai_disclaimer_injection_frequenc.md · reported by cisco-skill-scanner
1 UNANALYZABLE_BINARY
Files: /repo/rag_engine/requirements_frozen.txt · reported by cisco-skill-scanner
1 YARA_prompt_injection_generic
Files: /repo/rag_engine/api/app.py · reported by cisco-skill-scanner