Loading the registry…
Software architecture workflow that diagnoses architecture problems, selects the right analysis method, compares options, synthesizes stakeholder input, and produces a recommendation, review, or ADR
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.
9 critical findings reported by cisco-skill-scanner, agent-audit-kit, 5 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 -- 'first-fluke/mapple (architecture)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'first-fluke/mapple (architecture)' ~/.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
13 findings · 0.8s
v2.0.11
801 findings · 28.4s
v0.3.74
67 findings · 14.5s
v0.1.0
4 findings · 6.9s
v0.1.0
7 findings · 7.0s
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.
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 892 findings across every scanner that examined this package. 4 of 9 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 16 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.
42 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, AAK-AGENT-005, FILE_MAGIC_MISMATCH and 3 more · Files: AGENTS.md, CLAUDE.md, /repo/apps/web/CLAUDE.md and 32 more · reported by agent-audit-kit, cisco-skill-scanner
19 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_script_injection_generic, AAK-IPI-WILD-CORPUS-001, SECRET_PASSWORD_VAR and 3 more · Files: /repo/apps/api/tests/test_injection.py, apps/api/tests/test_injection.py, /repo/apps/api/tests/test_auth_security.py and 3 more · reported by cisco-skill-scanner, agent-audit-kit
17 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: AAK-SKILL-004, YARA_autonomy_abuse_generic, AAK-AGENT-TRUST-004 and 2 more · Files: .codex/skills/docs/SKILL.md, .claude/skills/docs/SKILL.md, .gemini/skills/docs/SKILL.md and 8 more · reported by agent-audit-kit, cisco-skill-scanner
6 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: AAK-GHA-IMMUTABLE-001, MANIFEST_INVALID_NAME · Files: .github/workflows/ci.yml, .github/workflows/terraform.yml, .github/workflows/deploy-web.yml and 1 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.
353 HIDDEN_DATA_FILE
Files: /repo/.mise.toml, /repo/.agents/skills/oma-orchestrator/resources/subagent-prompt-template.md, /repo/.agents/skills/oma-frontend/resources/checklist.md and 349 more · reported by cisco-skill-scanner
175 MANIFEST_MISSING_LICENSE
Files: /repo/.codex/skills/deepsec/SKILL.md, /repo/.codex/skills/scm/SKILL.md, /repo/.codex/skills/work/SKILL.md and 172 more · reported by cisco-skill-scanner
67 YARA_autonomy_abuse_generic
Files: /repo/.codex/skills/work/SKILL.md, /repo/.gemini/skills/work/SKILL.md, /repo/.qwen/skills/work/SKILL.md and 1 more · reported by cisco-skill-scanner
55 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/apps/api/SKILL.md, /repo/apps/web/SKILL.md and 52 more · reported by cisco-skill-scanner
34 HIDDEN_EXECUTABLE_SCRIPT
Files: /repo/.agents/skills/oma-orchestrator/scripts/parallel-run.sh, /repo/.agents/hooks/core/keyword-detector.ts, /repo/.agents/hooks/core/state-emit.ts and 31 more
16 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: HIDDEN_DATA_FILE · Files: /repo/.agents/skills/oma-debug/resources/examples.md, /repo/.agents/skills/oma-market/resources/examples.md, /repo/.agents/skills/oma-tf-infra/resources/multi-cloud-examples.md and 13 more · reported by cisco-skill-scanner
Critical command injection and path traversal risks identified.
The artifact contains critical command injection vulnerabilities in JavaScript child processes, specifically in `/repo/.agents/hooks/variants/opencode/oma.ts` and `/repo/.agents/hooks/variants/pi/index.ts`, allowing for shell execution. A path traversal vulnerability is present in `.agents/hooks/core/persistent-mode.ts`, which could enable unauthorized file access. Additionally, high-severity findings indicate potential for secrets to be sent over the network and the presence of hidden executable 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.
18 DATA_EXFIL_JS_NETWORK
Files: /repo/apps/web/src/app/(main)/settings/export/page.tsx, /repo/apps/web/src/components/auth/auth-bootstrap.tsx, /repo/apps/web/src/components/globe/globe-view.tsx and 4 more · reported by cisco-skill-scanner
16 AAK-AGENT-TRUST-004
Files: .gemini/skills/deepsec/SKILL.md, .gemini/skills/scm/SKILL.md, .gemini/skills/work/SKILL.md and 13 more · reported by agent-audit-kit
8 LOW_ANALYZABILITY
Files: /repo/apps/web, /repo/.agents/hooks/variants/pi, /repo/.agents/skills/oma-hwp and 5 more · reported by cisco-skill-scanner
7 AAK-MCP-ATTEST-001
Files: .mcp.json, .gemini/settings.json, .agents/mcp.json and 1 more · reported by agent-audit-kit
4 AAK-HEALTHCARE-AI-004
Files: .claude/agents/debug-investigator.md, .gemini/agents/debug-investigator.md, .agents/agents/debug-investigator.md and 1 more · reported by agent-audit-kit
4 AAK-MCP-006
Files: .mcp.json, .gemini/settings.json, .agents/mcp.json and 1 more · reported by agent-audit-kit
4 EXCESSIVE_FILE_COUNT
Files: /repo/., /repo/apps/web/., /repo/apps/api/. and 1 more · reported by cisco-skill-scanner
4 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/.agents/skills/oma-dev-workflow/SKILL.md, /repo/.agents/skills/oma-hwp/resources/execution-protocol.md, /repo/.agents/skills/oma-pdf/resources/execution-protocol.md and 1 more · reported by nerlo-install-instruction
3 AAK-MCP-005
Files: .gemini/settings.json, .agents/mcp_config.json · reported by agent-audit-kit
3 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/.agents/hooks/variants/opencode/oma.ts, /repo/.agents/hooks/variants/pi/index.ts · reported by cisco-skill-scanner
3 MANIFEST_INVALID_NAME
Files: /repo/.agents/skills/oma-observability/resources/layers/L7-application/SKILL.md, /repo/.agents/skills/_shared/SKILL.md, /repo/apps/mobile/ios/Runner/Assets.xcassets/LaunchImage.imageset/SKILL.md · reported by cisco-skill-scanner
3 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/apps/web/src/components/auth/auth-bootstrap.tsx, /repo/apps/web/src/lib/auth/api-client.ts, /repo/apps/web/src/lib/auth/logout.ts · reported by nerlo-behavioral
2 AAK-LEGAL-001
Files: packages/types/package.json, apps/web/package.json · reported by agent-audit-kit
2 opt.nerlo-rules.nerlo-install-shell-inline-command
Files: /repo/.agents/skills/oma-observability/resources/examples.md, /repo/.agents/skills/oma-refactor/resources/measurement.md · reported by nerlo-install-instruction
2 PIPELINE_TAINT_FLOW
Files: /repo/.agents/skills/oma-dev-workflow/SKILL.md · reported by cisco-skill-scanner
1 AAK-LEGAL-002
Files: .agents/skills/oma-hwp/resources/package.json · reported by agent-audit-kit
1 AAK-MCP-AUTH-PATHTRAVERSAL-001
Files: .agents/hooks/core/persistent-mode.ts · reported by agent-audit-kit
1 AAK-OAUTH-007
Files: apps/api/src/auth/oauth.py · reported by agent-audit-kit
1 AAK-SKILL-001
Files: .agents/skills/oma-dev-workflow/SKILL.md · reported by agent-audit-kit
1 AAK-STATE-PRIVACY-002
Files: .agents/skills/oma-observability/resources/signals/privacy.md · reported by agent-audit-kit
1 AAK-STATE-PRIVACY-003
Files: .agents/skills/oma-observability/resources/signals/privacy.md · reported by agent-audit-kit
1 AAK-TRUST-004
Files: .claude/settings.json · reported by agent-audit-kit
1 AAK-TRUST-006
Files: .claude/settings.json · reported by agent-audit-kit
1 AAK-TRUST-007
Files: .claude/settings.json · reported by agent-audit-kit
1 agents-comment-injection-186
Files: agents/qa-reviewer.md · reported by agentshield
1 agents-comment-injection-198
Files: agents/pm-planner.md · reported by agentshield
1 agents-comment-injection-211
Files: agents/backend-engineer.md · reported by agentshield
1 agents-comment-injection-235
Files: agents/mobile-engineer.md · reported by agentshield
1 agents-comment-injection-240
Files: agents/db-engineer.md · reported by agentshield
1 agents-comment-injection-243
Files: agents/debug-investigator.md · reported by agentshield
1 agents-comment-injection-246
Files: agents/frontend-engineer.md · reported by agentshield
1 agents-comment-injection-262
Files: agents/architecture-reviewer.md · reported by agentshield
1 agents-comment-injection-272
Files: agents/tf-infra-engineer.md · reported by agentshield
1 agents-comment-injection-297
Files: agents/docs-curator.md · reported by agentshield
1 agents-comment-injection-308
Files: agents/refactor-engineer.md · reported by agentshield
1 agents-comment-injection-372
Files: agents/research-explorer.md · reported by agentshield
1 opt.nerlo-rules.nerlo-hardcoded-external-egress
Files: /repo/apps/web/src/components/globe/globe-view.tsx · reported by nerlo-behavioral
1 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/.agents/skills/oma-orchestrator/SKILL.md · reported by nerlo-install-instruction
1 permissions-no-deny-list
Files: settings.json · reported by agentshield
1 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/repo/.design-context.md · reported by cisco-skill-scanner
Showing 25 of 66; the rest are in the per-scanner reports above.