Loading the registry…
Governance-first runtime for AI agents (NDJSON receipts, SPC-grade quality gates)
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.
92 critical findings reported by cisco-skill-scanner, agent-audit-kit, 36 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 -- vnx-orchestration
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- vnx-orchestration ~/.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
25 findings · 0.8s
v2.0.11
683 findings · 119.8s
v0.3.74
126 findings · 259.2s
v0.2.0
9 findings · 39.4s
v0.2.0
25 findings · 39.5s
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 · 1.0s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image.
5 scans on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Sep 16, 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 |
| Sep 11, 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 |
| Aug 1, 2026 | Flagged11 | — | agentshield: completecisco-skill-scanner ·!: timeoutagent-audit-kit ·!: timeoutnerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source ·n/a: not applicabletrivy: completeosv-scanner: complete | completed |
| Jul 30, 2026 | Flagged0 | — | cisco-skill-scanner ·!: timeoutagent-audit-kit ·!: timeoutnerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source ·n/a: not applicabletrivy: completeosv-scanner: completetrivy_image ·n/a: not applicable | completed |
| Jul 29, 2026 | Scan Halted | — | cisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-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 868 findings across every scanner that examined this package. 56 of 92 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 7 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.
197 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: COMPOUND_FIND_EXEC, PIPELINE_TAINT_FLOW, FIND_EXEC_PATTERN and 11 more · Files: /repo/docs/_archive/operations/SKILL.md, /repo/docs/_archive/operations/wave1-rollback.md, /repo/docs/core/SKILL.md and 46 more · reported by cisco-skill-scanner, nerlo-install-instruction, agent-audit-kit
153 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_command_injection_generic, YARA_sql_injection_generic, TOOL_ABUSE_SYSTEM_MODIFICATION and 15 more · Files: /repo/tests/test_kimi_spawn_heartbeat.py, /repo/tests/test_pool_worktree_manager.py, /repo/tests/test_tmux_interactive_dispatch.py and 73 more · reported by cisco-skill-scanner, agent-audit-kit
17 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: agents-comment-injection-0, AAK-AGENT-003, agents-encoded-payload-1744 and 5 more · Files: terminals/T0/CLAUDE.md, CLAUDE.md, terminals/T3/CLAUDE.md and 3 more · reported by agentshield, agent-audit-kit, nerlo-install-instruction
1 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/.github/workflows/anchor-immutability-check.yml · 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.
116 MANIFEST_MISSING_LICENSE
Files: /repo/.claude/skills/backend-developer/SKILL.md, /repo/.claude/skills/supabase-expert/SKILL.md, /repo/.claude/skills/t0-orchestrator/SKILL.md and 113 more · reported by cisco-skill-scanner
72 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/.claude/skills/intelligence-engineer/SKILL.md, /repo/.claude/skills/database-engineer/SKILL.md, /repo/agents/orchestrator/.claude/skills/orchestrate/SKILL.md and 69 more · reported by cisco-skill-scanner
52 AAK-SECRET-004
Files: dashboard/serve_dashboard.py, scripts/gather_intelligence.py, scripts/roadmap_manager.py and 8 more · reported by agent-audit-kit
33 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/scripts/benchmark/field-tests/runners/check_openrouter_credits.py, /repo/scripts/conversation_analyzer/deep_analyzer.py, /repo/scripts/lib/adapters/ollama_adapter.py and 6 more · reported by cisco-skill-scanner
22 MANIFEST_INVALID_NAME
Files: /repo/scripts/benchmark/field-tests/tasks/t4_frontier/01_path_sandbox/SKILL.md, /repo/scripts/benchmark/field-tests/tasks/t5_review_design/02_agent_engine_design/SKILL.md, /repo/.claude/terminals/T3/SKILL.md and 19 more
The model could have called any of these a false positive and did not.
1 SQL_INJECTION_STRING_FORMAT
Files: /repo/vnx_cli/commands/doctor.py · reported by cisco-skill-scanner
4 The model did not answer for these findings.
Rules: DATA_EXFIL_NETWORK_REQUESTS, GLOB_HIDDEN_FILE_TARGETING · Files: /repo/tests/test_dashboard_sync.py, /repo/tests/test_role_sync.py · reported by cisco-skill-scanner
3 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: HIDDEN_DATA_FILE · Files: /repo/.vnx/vnx_workers.examples/six_worker_pool.yaml, /repo/.vnx/vnx_workers.examples/single_worker.yaml, /repo/.vnx/vnx_workers.examples/provider_mix.yaml · reported by cisco-skill-scanner
Critical risks: command execution, SQL injection, data exfiltration, and path traversal.
The artifact contains multiple critical findings related to command injection, SQL injection, and data exfiltration. Specifically, shell execution is possible via `eval` and `os.system` in several scripts, and SQL injection vulnerabilities are present in database interaction code. Network egress is identified through socket connections, and a path traversal vulnerability exists in a session resolver script. These capabilities could lead to unauthorized system access, data manipulation, or information disclosure.
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.
20 DATA_EXFIL_JS_NETWORK
Files: /repo/dashboard/token-dashboard/app/agent-stream/page.tsx, /repo/dashboard/token-dashboard/lib/api.ts, /repo/dashboard/token-dashboard/lib/operator-api.ts · reported by cisco-skill-scanner
16 AAK-IPI-WILD-CORPUS-001
Files: vnx_cli/_reexec.py, scripts/migrate_to_central_vnx.py, scripts/quality_db_init.py and 12 more · reported by agent-audit-kit
16 YARA_autonomy_abuse_generic
Files: /repo/scripts/gate_obligation_runner.py, /repo/scripts/lib/dispatch_cli.py · reported by cisco-skill-scanner
15 YARA_sql_injection_generic
Files: /repo/skills/supabase-expert/scripts/analyze_database.py, /repo/scripts/benchmark/field-tests/tasks/t5_review_design/01_planted_review/verify.py · reported by cisco-skill-scanner
12 HIDDEN_DATA_FILE
Files: /repo/scripts/benchmark/field-tests/tasks/t1_trivial/03_dotenv_script/seed/.env, /repo/.geminiignore, /repo/dashboard/token-dashboard/test-results/.last-run.json and 6 more · reported by cisco-skill-scanner
11 hooks-silent-fail-52
Files: settings.json · reported by agentshield
11 RESOURCE_ABUSE_INFINITE_LOOP
Files: /repo/dashboard/api_agent_stream.py, /repo/dashboard/api_intelligence.py, /repo/dashboard/api_register_stream.py and 5 more · reported by cisco-skill-scanner
11 SQL_INJECTION_STRING_FORMAT
Files: /repo/scripts/benchmark/field-tests/tasks/t3_complex/09_mock_introspection_trap/seed/builders.py, /repo/scripts/benchmark/field-tests/runners/skill_smoke.py, /repo/scripts/benchmark/fts5_rebuild_benchmark.py and 2 more · reported by cisco-skill-scanner
10 FILE_MAGIC_MISMATCH
Files: /repo/scripts/f39/__init__.py, /repo/scripts/lib/provider_spawns/__init__.py, /repo/scripts/lib/providers/__init__.py and 7 more · reported by cisco-skill-scanner
8 PIPELINE_TAINT_FLOW
Files: /repo/.claude/terminals/T0/role-orchestrator.md, /repo/.claude/terminals/T0/SKILL.md, /repo/.claude/skills/fabric-reference/SKILL.md and 1 more · reported by cisco-skill-scanner
8 YARA_code_execution_generic
Files: /repo/scripts/benchmark/prompts/02_code_review.txt, /repo/scripts/benchmark/results/deepseek-v4-pro__02_code_review.json, /repo/scripts/benchmark/results/glm-5-1__02_code_review.json and 2 more · reported by cisco-skill-scanner
6 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/claudedocs/blocked-track-triage-b.md, /repo/dashboard/README.md, /repo/install-remote.sh and 2 more · reported by nerlo-install-instruction
6 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/scripts/benchmark/field-tests/runners/check_openrouter_credits.py, /repo/scripts/benchmark/field-tests/tasks/t5_review_design/01_planted_review/seed/seoaudit/serp_client.py, /repo/scripts/lib/dispatch_cli.py and 2 more · reported by nerlo-behavioral
4 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/dashboard/token-dashboard/scripts/validate_test_fixtures.ts · reported by cisco-skill-scanner
3 COMMAND_INJECTION_EVAL
Files: /repo/scripts/benchmarks/run_lane_bench.py, /repo/scripts/hooks/pretooluse_spawn_detector.py, /repo/scripts/llm_benchmark.py · reported by cisco-skill-scanner
3 SECRET_CONNECTION_STRING
Files: /repo/skills/supabase-expert/scripts/analyze_database.py · reported by cisco-skill-scanner
3 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/repo/CHANGELOG.md, /repo/scripts/benchmark/field-tests/repo/scripts/benchmark/field-tests/METHODOLOGY.md, /repo/scripts/benchmark/field-tests/tasks/t5_review_design/01_planted_review/repo/scripts/benchmark/field-tests/tasks/t5_review_design/01_planted_review/instruction.md · reported by cisco-skill-scanner
2 COMMAND_INJECTION_SHELL_TRUE
Files: /repo/scripts/lib/dispatch_sidedoor_audit.py · reported by cisco-skill-scanner
2 EXCESSIVE_FILE_COUNT
Files: /repo/dashboard/., /repo/. · reported by cisco-skill-scanner
2 FIND_EXEC_PATTERN
Files: /repo/scripts/daily_log_rotation.sh · reported by cisco-skill-scanner
2 hooks-silent-fail-46
Files: settings.json · reported by agentshield
2 LOW_ANALYZABILITY
Files: /repo/dashboard, /repo/scripts/benchmark/field-tests/tasks/t1_trivial/02_rls_policy · reported by cisco-skill-scanner
2 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/install-remote.sh · reported by nerlo-install-instruction
2 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/dashboard/token-dashboard/lib/api.ts · reported by nerlo-behavioral
2 YARA_command_injection_generic
Files: /repo/scripts/benchmark/results/claude-sonnet-4-6__02_code_review.json, /repo/scripts/benchmark/results/deepseek-v4-flash__02_code_review.json · reported by cisco-skill-scanner
1 AAK-LEGAL-002
Files: dashboard/token-dashboard/package.json · reported by agent-audit-kit
1 AAK-MCP-AUTH-PATHTRAVERSAL-001
Files: scripts/lib/append_receipt_internals/session_resolver.py · reported by agent-audit-kit
1 AAK-SKILL-004
Files: .claude/skills/pm/SKILL.md · reported by agent-audit-kit
1 AAK-TASKS-003
Files: scripts/llm_benchmark.py · reported by agent-audit-kit
1 AAK-TRUST-004
Files: .claude/settings.json · reported by agent-audit-kit
1 COMMAND_INJECTION_OS_SYSTEM
Files: /repo/scripts/vnx_init.py · reported by cisco-skill-scanner
1 COMPOUND_FIND_EXEC
Files: /repo/scripts/cleanup_massive_logs.sh · reported by cisco-skill-scanner
1 DATA_EXFIL_SOCKET_CONNECT
Files: /repo/scripts/lib/provider_spawns/glm_harness_spawn.py · reported by cisco-skill-scanner
1 GLOB_HIDDEN_FILE_TARGETING
Files: /repo/scripts/f39/gate_locks.py · reported by cisco-skill-scanner
1 hooks-chained-commands-0
Files: settings.json · reported by agentshield
1 hooks-chained-commands-1
Files: settings.json · reported by agentshield
1 hooks-logging-disabled-321
Files: settings.json · reported by agentshield
1 hooks-silent-fail-109
Files: settings.json · reported by agentshield
1 hooks-silent-fail-140
Files: settings.json · reported by agentshield
1 hooks-silent-fail-169
Files: settings.json · reported by agentshield
1 hooks-silent-fail-63
Files: settings.json · reported by agentshield
1 opt.nerlo-rules.nerlo-py-dynamic-exec
Files: /repo/scripts/lib/adapters/_litellm_agentic_runner.py · reported by nerlo-behavioral
1 permissions-no-deny-list
Files: settings.json · reported by agentshield
Showing 25 of 142; the rest are in the per-scanner reports above.