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.
272 critical findings reported by cisco-skill-scanner, agent-audit-kit, 246 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 -- thanos
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
Incomplete run
11 findings · 1.4s
v2.0.11
1604 findings · 151.4s
v0.3.74
148 findings · 90.3s
v0.1.0
53 findings · 118.2s
v0.1.0
64 findings · 118.3s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 0.8s
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 20, 2026 | Scan Halted | — | agentshield ·!: incompletecisco-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 1,880 findings across every scanner that examined this package. 2 of 272 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 1,114 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.
410 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: opt.nerlo-rules.nerlo-install-pipe-to-shell, FIND_EXEC_PATTERN, YARA_autonomy_abuse_generic and 1 more · Files: /repo/docs/mcp-deployment-guide.md, /repo/docs/adr/SKILL.md, /repo/docs/SKILL.md and 1 more · reported by nerlo-install-instruction, cisco-skill-scanner
11 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: YARA_sql_injection_generic, HIDDEN_EXECUTABLE_SCRIPT, LOW_ANALYZABILITY and 1 more · Files: /repo/tests/unit/test_neo4j_security_injection_prevention.py, /repo/.auto-claude/worktrees/tasks/054-enhanced-telegram-bot-experience/test_button_handlers_integration.py, /repo/mcp-servers/workos-mcp/src/__tests__ and 7 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, AAK-HEALTHCARE-AI-004 · Files: AGENTS.md, /repo/repo/AGENTS.md, /repo/Skills/repo/Skills/CLAUDE.md and 6 more · reported by agent-audit-kit, cisco-skill-scanner
9 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: FILE_MAGIC_MISMATCH · Files: /repo/.auto-claude/specs/022-pre-compile-agent-keyword-patterns-for-o-1-intent-/build-progress.txt, /repo/.auto-claude/specs/025-async-file-i-o-for-usage-tracking-to-prevent-main-/build-progress.txt, /repo/.auto-claude/specs/028-add-python-linting-configuration-ruff-flake8/build-progress.txt and 3 more · reported by cisco-skill-scanner
The model could have called any of these a false positive and did not.
95 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/Skills/monarch-money/lib/cache/PersistentCache.ts, /repo/Skills/monarch-money/lib/client/auth/SessionStorage.ts, /repo/mcp-servers/oura-mcp/src/api/oauth.ts and 10 more · reported by cisco-skill-scanner
62 DATA_EXFIL_JS_NETWORK
Files: /repo/Skills/monarch-money/lib/client/auth/AuthenticationService.ts, /repo/Skills/monarch-money/lib/client/auth/DirectAuthenticationService.ts, /repo/Skills/monarch-money/lib/client/graphql/GraphQLClient.ts and 13 more · reported by cisco-skill-scanner
37 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/Skills/gemini-deep-research/scripts/deep_research.py, /repo/Skills/gemini/gemini_cli.py, /repo/Shell/lib/notifications.py and 7 more · reported by cisco-skill-scanner
29 AAK-SECRET-004
Files: thanos.py, scripts/thanos-voice-response.py, scripts/graphiti-daily-digest.py and 10 more · reported by agent-audit-kit
20 LOW_ANALYZABILITY
Files: /repo/plugins/cache/thedotmack/claude-mem/9.0.0/scripts, /repo/mcp-servers/workos-mcp/src/services, /repo/mcp-servers/oura-mcp/src and 17 more · reported by cisco-skill-scanner
703 The review budget for this scan was already spent before these findings were reached.
Rules: FILE_MAGIC_MISMATCH, DATA_EXFIL_NETWORK_REQUESTS, AAK-OAUTH-007 and 42 more · Files: /repo/.claude/helpers/github-safe.js, /repo/Tools/adapters/google_calendar/legacy.py, /repo/docs/reports/validation-report.txt and 389 more · reported by cisco-skill-scanner, agent-audit-kit, agentshield and 2 more
337 The review call did not complete.
Rules: COMMAND_INJECTION_JS_CHILD_PROCESS, COMMAND_INJECTION_JS_FUNCTION_CONSTRUCTOR, COMMAND_INJECTION_EVAL and 27 more · Files: /repo/.claude/helpers/github-safe.js, /repo/.claude/helpers/metrics-db.mjs, /repo/.claude/statusline.mjs and 86 more · reported by cisco-skill-scanner, agent-audit-kit, nerlo-behavioral and 1 more
74 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: YARA_coercive_injection_generic, PDF_STRUCTURAL_THREAT, HIDDEN_EXECUTABLE_SCRIPT and 11 more · Files: /repo/data/galaxy_docs/orders_hod/14ewvImuAu-twHGduIqOZ8U5ELBm-uwrR__Notes Setup and Support Guide.pdf, /repo/data/galaxy_docs/orders_hod/1rp4D5PNQ9J6ELUkXnDKkeOTcl6R7AL2h__Manage Orders Activity Setup and Support Guide.pdf, /repo/.auto-claude/worktrees/tasks/054-enhanced-telegram-bot-experience/verify_response_times.py and 40 more · reported by cisco-skill-scanner, agent-audit-kit, agentshield
Critical command injection and data exposure risks.
The artifact exhibits extensive command injection vulnerabilities, including in JavaScript child processes and `eval` contexts, enabling arbitrary shell execution. Critical SQL injection risks are present, including an LLM-related RCE in `Memory/retrieval.ts`. Credential exposure is indicated in `Tools/security_utils.py`, alongside path traversal in `Tools/session_messenger.py`. High severity findings also highlight file system access, data exfiltration, and network egress of secrets.
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.
17 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/Shell/lib/notifications.py, /repo/Shell/lib/voice.py, /repo/Shell/lib/voice_designer.py and 9 more · reported by nerlo-behavioral
10 AAK-TASKS-003
Files: Tools/energy_aware_tasks.py, Tools/alert_checker.py, adapters/workos_adapter.py and 7 more · reported by agent-audit-kit
9 AAK-LEGAL-002
Files: package.json, model-escalator/package.json, dashboard/frontend/package.json and 6 more · reported by agent-audit-kit
9 OBFUSCATION_HEX_BLOB
Files: /repo/plugins/cache/thedotmack/claude-mem/9.0.0/scripts/worker-service.cjs · reported by cisco-skill-scanner
8 SQL_INJECTION_STRING_FORMAT
Files: /repo/Tools/state_store/store.py, /repo/Tools/intelligent_memory.py · reported by cisco-skill-scanner
4 FILE_MAGIC_MISMATCH
Files: /repo/dashboard/requirements.txt, /repo/model-escalator/requirements.txt · reported by cisco-skill-scanner
4 GLOB_HIDDEN_FILE_TARGETING
Files: /repo/hooks/thanos-status.sh · reported by cisco-skill-scanner
4 YARA_sql_injection_generic
Files: /repo/scripts/init_neon_db.py · reported by cisco-skill-scanner
3 HIDDEN_EXECUTABLE_SCRIPT
Files: /repo/.auto-claude/worktrees/tasks/056-proactive-context-surfacing/Tools/entity_extractor.py, /repo/.auto-claude/worktrees/tasks/054-enhanced-telegram-bot-experience/Tools/telegram_bot.py, /repo/.auto-claude/worktrees/tasks/056-proactive-context-surfacing/Tools/proactive_context.py · reported by cisco-skill-scanner
2 AAK-SECRET-001
Files: Tools/security_utils.py · reported by agent-audit-kit
2 TOOL_ABUSE_SYSTEM_MODIFICATION
Files: /repo/Access/install_tailscale.sh · reported by cisco-skill-scanner
1 AAK-LITELLM-CVE-2026-30623-PIN-001
Files: requirements.txt · reported by agent-audit-kit
1 AAK-LLM-SQL-RCE-001
Files: Memory/retrieval.ts · reported by agent-audit-kit
1 AAK-MCP-001
Files: .cursor/mcp.json · reported by agent-audit-kit
1 AAK-MCP-002
Files: plugins/cache/thedotmack/claude-mem/9.0.0/.mcp.json · reported by agent-audit-kit
1 AAK-MCP-AUTH-PATHTRAVERSAL-001
Files: Tools/session_messenger.py · reported by agent-audit-kit
1 AAK-MCP-LITELLM-CVE-2026-59822-001
Files: requirements.txt · reported by agent-audit-kit
1 AAK-MCP-NOAUTH-DEFAULT
Files: scripts/thanos-voice-response.py · reported by agent-audit-kit
1 AAK-MCP-STDIO-CMD-INJ-002
Files: mcp-servers/todoist-mcp/src/index.ts · reported by agent-audit-kit
1 AAK-MCP-TOOLGATE-ASYMMETRY-001
Files: Tools/adapters/neo4j_adapter.py · reported by agent-audit-kit
1 hooks-file-delete-746
Files: hooks/smart-swarm-cleanup.sh · reported by agentshield
1 permissions-no-deny-list
Files: settings.json · reported by agentshield
Showing 25 of 25; the rest are in the per-scanner reports above.