Loading the registry…
Push the LLM to reconsider, refine, and improve its recent output.
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.
Claude Skills install to a single target, no runtime picker.
nerlo install -- 'ashkaji/zachai (bmad-advanced-elicitation)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'ashkaji/zachai (bmad-advanced-elicitation)' ~/.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
14 findings · 0.5s
v2.0.11
Timed out
0 findings · 300.0s
v0.3.74
272 findings · 142.5s
v0.1.0
19 findings · 57.3s
v0.1.0
85 findings · 57.5s
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 · 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 22, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner ·!: timeoutagent-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 390 findings across every scanner that examined this package.
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.
1 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-TASKS-003 · Files: src/workers/label-studio-ml-bridge/test_model.py · reported by agent-audit-kit
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.
146 AAK-AGENT-TRUST-004
Files: .gemini/skills/bmad-testarch-atdd/atdd-checklist-template.md, .gemini/skills/bmad-testarch-test-design/test-design-qa-template.md, .gemini/skills/bmad-bmb-setup/SKILL.md and 143 more · reported by agent-audit-kit
80 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/.bmad-outputs/implementation-artifacts/archive/16-5-ui-manager-invite-transcripteur-expert.md, /repo/.bmad-outputs/implementation-artifacts/archive/2-2-project-creation-label-studio-provisioning.md, /repo/.claude/skills/bmad-tea/resources/knowledge/ci-burn-in.md and 73 more · reported by nerlo-install-instruction
72 AAK-IPI-WILD-CORPUS-001
Files: .claude/skills/bmad-testarch-automate/resources/knowledge/ci-burn-in.md, .claude/skills/bmad-testarch-automate/resources/knowledge/nfr-criteria.md, .claude/skills/bmad-testarch-atdd/resources/knowledge/ci-burn-in.md and 69 more · reported by agent-audit-kit
35 AAK-HEALTHCARE-AI-004
Files: .claude/skills/bmad-agent-tech-writer/SKILL.md, .claude/skills/bmad-editorial-review-prose/workflow.md, .claude/skills/bmad-cis-problem-solving/workflow.md and 32 more · reported by agent-audit-kit
13 AAK-SECRET-004
Files: src/scripts/bootstrap_models.py, src/workers/diarization-worker/main.py, src/workers/camunda-worker/provision_label_studio.py and 6 more · reported by agent-audit-kit
Artifact includes secrets, performs dynamic execution, and can initiate network egress.
The artifact contains embedded secrets and is capable of dynamic code execution. It can also transmit sensitive information, including secrets, over the network. Furthermore, the artifact includes directives for installing reverse shells and running bundled executables, indicating potential for broad system interaction.
Concern level assessed by the review: High. 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.
12 opt.nerlo-rules.nerlo-py-dynamic-exec
Files: /repo/.claude/skills/bmad-agent-builder/scripts/generate-html-report.py, /repo/.claude/skills/bmad-workflow-builder/scripts/generate-convert-report.py, /repo/.claude/skills/bmad-workflow-builder/scripts/generate-html-report.py and 9 more · reported by nerlo-behavioral
5 opt.nerlo-rules.nerlo-install-reverse-shell-directive
Files: /repo/.bmad-outputs/implementation-artifacts/archive/1-2-keycloak-multi-roles.md · reported by nerlo-install-instruction
5 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/src/scripts/ingest_bible.py, /repo/src/workers/diarization-worker/bootstrap_sherpa.py, /repo/src/workers/diarization-worker/engines/sherpa_engine.py · reported by nerlo-behavioral
2 AAK-LEGAL-002
Files: src/frontend/package.json, src/collab/hocuspocus/package.json · reported by agent-audit-kit
2 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/src/collab/hocuspocus/src/index.ts, /repo/src/frontend/src/features/project-wizard/NewProjectWizard.tsx · reported by nerlo-behavioral
1 AAK-OAUTH-007
Files: src/api/fastapi/keycloak_admin.py · reported by agent-audit-kit
1 AAK-TRUST-004
Files: .claude/settings.local.json · reported by agent-audit-kit
1 AAK-TRUST-006
Files: .claude/settings.local.json · reported by agent-audit-kit
1 hooks-no-pretooluse
Files: settings.local.json · reported by agentshield
1 permissions-no-deny-list
Files: settings.local.json · reported by agentshield
1 permissions-permissive-Bash(docker compose:*)
Files: settings.local.json · reported by agentshield
1 permissions-permissive-Bash(docker exec:*)
Files: settings.local.json · reported by agentshield
1 permissions-permissive-Bash(docker ps:*)
Files: settings.local.json · reported by agentshield
1 permissions-permissive-Bash(docker restart:*)
Files: settings.local.json · reported by agentshield
1 permissions-permissive-Bash(docker run:*)
Files: settings.local.json · reported by agentshield
1 permissions-permissive-Bash(python -m pytest src/api/fastapi/test_main.py -v --tb=short)
Files: settings.local.json · reported by agentshield
1 permissions-permissive-Bash(python -m pytest src/api/fastapi/test_main.py -x)
Files: settings.local.json · reported by agentshield
1 permissions-permissive-Bash(python -m pytest src/api/fastapi/test_main.py::test_create_project_duplicate_name -xvs)
Files: settings.local.json · reported by agentshield
1 permissions-permissive-Bash(python -m pytest src/api/fastapi/test_main.py::test_create_project_invalid_production_goal -xvs)
Files: settings.local.json · reported by agentshield
1 permissions-permissive-Bash(python -m pytest test_main.py -v --tb=line)
Files: settings.local.json · reported by agentshield
1 permissions-permissive-Bash(python -m pytest test_main.py -v --tb=short)
Files: settings.local.json · reported by agentshield
1 permissions-permissive-Bash(python -m pytest test_main.py -v)
Files: settings.local.json · reported by agentshield
Showing 25 of 123; the rest are in the per-scanner reports above.