Loading the registry…
Claude Skills are markdown + scripts loaded into Claude Code; 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.
80 critical findings reported by cisco-skill-scanner, agent-audit-kit, 28 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
Claude Skills install to a single target, no runtime picker.
nerlo install -- cortex
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- cortex ~/.claude/skills/
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.
v1.4.0
6 findings · 0.6s
v2.0.11
556 findings · 276.3s
v0.3.74
114 findings · 436.6s
v0.1.0
1 finding · 37.5s
v0.1.0
3 findings · 37.6s
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 · 0.9s
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 22, 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 680 findings across every scanner that examined this package. 52 of 80 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 68 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.
150 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: AAK-SECRET-003, YARA_script_injection_generic, COMMAND_INJECTION_EVAL and 26 more · Files: tests/golden/test_sync_policy.py, tests/orchestrators/e2e/test_lens_discovery_security_golden.py, tests/orchestrators/e2e/scenarios/lens/security/golden_37_secret_detection.yaml and 69 more · reported by agent-audit-kit, cisco-skill-scanner
148 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: PIPELINE_TAINT_FLOW, opt.nerlo-rules.nerlo-install-pipe-to-shell, YARA_prompt_injection_unicode_steganography and 7 more · Files: /repo/docs/.claude-code/00-cc-index.md, /repo/docs/.claude-code/02-cc-install.md, /repo/cortex-registry/_yaml-reader/tests/screenshots/01a-before-cards.png and 86 more · reported by cisco-skill-scanner, nerlo-install-instruction, agent-audit-kit
31 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-HEALTHCARE-AI-004, TOOL_ABUSE_UNDECLARED_NETWORK, HIDDEN_DATA_FILE and 1 more · Files: .github/prompts/cortex-doc.prompt.md, docs/.claude-code/knowledge/cc_agent_dev.yaml, docs/awakening-of-cortex/chapters/12-The-Enterprise-Brain.md and 20 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.
53 DATA_EXFIL_JS_NETWORK
Files: /repo/_workspaces/cortex-sts/CortexLabs/BadMonolith/frontend/src/app.ts, /repo/_workspaces/cortex-sts/CortexLabs/Refactored/frontend/src/api/apiClient.ts, /repo/_workspaces/cortex-sts/CortexLabs/Refactored/frontend/src/services/fintrackApi.ts and 9 more · reported by cisco-skill-scanner
47 FILE_MAGIC_MISMATCH
Files: /repo/cortex-registry/planning/phases/completed/phase-94-workflow-gateway-enforcement.yaml, /repo/cortex-registry/planning/phases/v2/artifacts/phase-m17/template_consolidation_delta.yaml, /repo/_workspaces/ado/integration/__init__.py and 29 more · reported by cisco-skill-scanner
24 AAK-SECRET-004
Files: _workspaces/cortex-sts/CortexLabs/BadMonolith/backend/appsettings.json, cortex/infrastructure/secrets/__init__.py, cortex/orchestrators/core/intent_router_impl.py and 4 more · reported by agent-audit-kit
23 MANIFEST_MISSING_LICENSE
Files: /repo/.claude/skills/cortex-architecture-review/SKILL.md, /repo/.claude/skills/cortex-claude-readiness/SKILL.md, /repo/.claude/skills/cortex-audit/SKILL.md and 20 more · reported by cisco-skill-scanner
23 SOCIAL_ENG_VAGUE_DESCRIPTION
68 The review budget for this scan was already spent before these findings were reached.
Rules: HIDDEN_DATA_FILE, EXCESSIVE_FILE_COUNT, MANIFEST_MISSING_LICENSE and 4 more · Files: /repo/docs/.content/11-patterns-knowledge-architecture.md, /repo/docs/.claude-code/knowledge/cc_skills_dev.yaml, /repo/docs/.content/00-mission.md and 58 more · reported by cisco-skill-scanner, nerlo-install-instruction
Critical command and SQL injection vulnerabilities detected
The artifact contains critical command injection vulnerabilities, including `eval` usage in `cortex/orchestrators/core/intent_router/challenge_generator.py` and JavaScript function constructor misuse in several vendor files, which could lead to shell execution. Multiple SQL injection vulnerabilities are present in database analyzer plugins and security test generation components, potentially allowing unauthorized database access. Additionally, the artifact has high-severity findings for embedded secrets and network egress of sensitive data.
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.
Files: /repo/.claude/skills/cortex-architecture-review/SKILL.md, /repo/.claude/skills/cortex-claude-readiness/SKILL.md, /repo/.claude/skills/cortex-audit/SKILL.md and 20 more · reported by cisco-skill-scanner
21 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/_workspaces/ado/ado_provider.py, /repo/cortex/mcp/tools/core.py, /repo/cortex/orchestrators/validation/pre_implementation_checklist.py and 5 more · reported by cisco-skill-scanner
15 YARA_sql_injection_generic
Files: /repo/cortex/lens/analyzers/postgresql_plugin.py, /repo/cortex/lens/analyzers/sqlserver_plugin.py, /repo/cortex/orchestrators/intelligence/security_test_generator.py and 1 more · reported by cisco-skill-scanner
14 HIDDEN_DATA_FILE
Files: /repo/_workspaces/cortex-sts/CortexLabs/.analysis/fintrack-refactoring-dashboard.html, /repo/.githooks/post-checkout, /repo/.pytest-ignore and 5 more · reported by cisco-skill-scanner
10 AAK-IPI-WILD-CORPUS-001
Files: cortex/infrastructure/database_health_verifier.py, cortex/infrastructure/env_initializer.py, cortex/core/mandatory_checkpoints.py and 7 more · reported by agent-audit-kit
7 COMMAND_INJECTION_EVAL
Files: /repo/cortex/orchestrators/core/intent_router/challenge_generator.py, /repo/cortex/tools/scaffolder_templates.py · reported by cisco-skill-scanner
5 RESOURCE_ABUSE_INFINITE_LOOP
Files: /repo/cortex/infrastructure/api/endpoints/lens_dashboard_routes.py, /repo/cortex/infrastructure/collaboration/operation_lock.py, /repo/cortex/infrastructure/connection_pool.py and 2 more · reported by cisco-skill-scanner
4 AAK-HEALTHCARE-AI-004
Files: _workspaces/recommendations/learning-path.md, cortex-registry/knowledge/INDEX.yaml, cortex-registry/knowledge/ai/ai-adoption-sparks.yaml and 1 more · reported by agent-audit-kit
4 COMMAND_INJECTION_JS_FUNCTION_CONSTRUCTOR
Files: /repo/cortex/dashboards/static/vendor/mermaid-10.6.1.min.js, /repo/cortex-registry/_yaml-reader/vendor/d3.min.js, /repo/cortex/dashboards/static/vendor/d3-7.8.5.min.js · reported by cisco-skill-scanner
4 EXCESSIVE_FILE_COUNT
Files: /repo/cortex-registry/workflows/templates/., /repo/cortex-registry/planning/., /repo/cortex-registry/workflows/. and 1 more · reported by cisco-skill-scanner
3 LOW_ANALYZABILITY
Files: /repo/_workspaces, /repo/_workspaces/cortex-sts, /repo/cortex-registry/plans · reported by cisco-skill-scanner
3 MANIFEST_INVALID_NAME
Files: /repo/_workspaces/SKILL.md, /repo/.claude/SKILL.md, /repo/_workspaces/.chats/SKILL.md · reported by cisco-skill-scanner
2 AAK-LEGAL-002
Files: _workspaces/cortex-sts/CortexLabs/Refactored/frontend/package.json, _workspaces/cortex-sts/CortexLabs/BadMonolith/frontend/package.json · reported by agent-audit-kit
2 AAK-TASKS-003
Files: cortex/models/plan_models.py, cortex/infrastructure/_quarantine/capacity__evidence_collector.py · reported by agent-audit-kit
2 YARA_command_injection_generic
Files: /repo/cortex-registry/knowledge-base/security/cicd-hardening.yaml, /repo/cortex-registry/knowledge/security/cicd-hardening.yaml · reported by cisco-skill-scanner
1 AAK-MCP-NOAUTH-DEFAULT
Files: cortex/infrastructure/database.py · reported by agent-audit-kit
1 AAK-METIS-SCORING-SINK-001
Files: cortex/orchestrators/core/bluf_system.py · reported by agent-audit-kit
1 AAK-OAUTH-008
Files: cortex/lens/analyzers/config_analyzer.py · reported by agent-audit-kit
1 AAK-SUPPLY-004
Files: pyproject.toml · reported by agent-audit-kit
1 AAK-TRUST-003
Files: .claude/settings.json · reported by agent-audit-kit
1 BINARY_FILE_DETECTED
Files: /repo/cortex-registry/company/dashboards/assets/images/cortex-logo-animated.mp4 · reported by cisco-skill-scanner
1 hooks-no-stop-hooks
Files: settings.json · reported by agentshield
1 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/_workspaces/cortex-sts/CortexLabs/BadMonolith/frontend/src/app.ts · reported by nerlo-behavioral
1 permissions-missing-deny->-/dev/
Files: settings.json · reported by agentshield
1 permissions-missing-deny-chmod-777
Files: settings.json · reported by agentshield
1 permissions-missing-deny-ssh
Files: settings.json · reported by agentshield
1 permissions-missing-deny-sudo
Files: settings.json · reported by agentshield
1 permissions-permissive-Bash(python3 scripts/run_tests.py *)
Files: settings.json · reported by agentshield
1 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/_workspaces/repo/_workspaces/cortex-v2-claude-agents-and-skills.md · reported by cisco-skill-scanner
1 UNANALYZABLE_BINARY
Files: /repo/cortex-registry/company/dashboards/assets/images/cortex-logo-animated.mp4 · reported by cisco-skill-scanner
1 YARA_code_execution_generic
Files: /repo/cortex/core/production_readiness_manager.py · reported by cisco-skill-scanner
1 YARA_prompt_injection_unicode_steganography
Files: /repo/cortex-registry/company/dashboards/assets/images/Awakening.png · reported by cisco-skill-scanner
Showing 25 of 71; the rest are in the per-scanner reports above.