Loading the registry…
View audit logs, decision traces, and session history for AI transparency. ACTION_TYPES (19 entries) include PDCA events (phase_transition, gate_passed/failed, agent_spawned/completed/failed, rollback_executed, destructive_blocked) and Sprint events (sprint_paused, sprint_resumed, master_plan_created — v2.1.13). Triggers: audit, log, decision trace, history
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.
88 critical findings reported by cisco-skill-scanner, agent-audit-kit, 30 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 -- 'ww-w-ai/bkit-claude-code (audit)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'ww-w-ai/bkit-claude-code (audit)' ~/.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
0 findings · 0.8s
v2.0.11
1392 findings · 89.6s
v0.3.74
52 findings · 37.0s
v0.1.0
0 findings · 13.4s
v0.1.0
62 findings · 13.4s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.2s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 1.2s
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 21, 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 1,506 findings across every scanner that examined this package. 58 of 88 findings rated critical by their scanner were among the dismissals.
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.
872 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: COMMAND_INJECTION_JS_CHILD_PROCESS, COMMAND_INJECTION_EVAL, DATA_EXFIL_JS_FS_ACCESS and 9 more · Files: /repo/tests/qa/bkit-deep-system.test.js, /repo/tests/qa/bkit-full-system.test.js, /repo/tests/qa/bug-fixes-v218.test.js and 236 more · reported by cisco-skill-scanner, agent-audit-kit
169 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: YARA_prompt_injection_generic, YARA_command_injection_generic, COMPOUND_FIND_EXEC and 13 more · Files: /repo/docs/archive/2026-05/04-report/features/cc-v2130-v2132-impact-analysis.report.md, /repo/docs/03-analysis/features/v2134-hook-reachability.analysis.en.md, /repo/docs/03-analysis/features/v2134-hook-reachability.analysis.ko.md and 74 more · reported by cisco-skill-scanner, nerlo-install-instruction, agent-audit-kit
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: AAK-AGENT-TRUST-001 · Files: .github/workflows/contract-check.yml · 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.
231 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/evals/ab-tester.js, /repo/evals/runner.js, /repo/hooks/session-start.js and 99 more · reported by cisco-skill-scanner
97 MANIFEST_MISSING_LICENSE
Files: /repo/skills/phase-9-deployment/SKILL.md, /repo/skills/phase-4-api/SKILL.md, /repo/skills/code-review/SKILL.md and 94 more · reported by cisco-skill-scanner
49 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/.claude/SKILL.md, /repo/bkit-system/SKILL.md and 46 more · reported by cisco-skill-scanner
20 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/lib/control/external-feedback-tracker.js, /repo/lib/core/worktree-detector.js, /repo/lib/defense/push-event-guard.js and 9 more · reported by cisco-skill-scanner
8 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/CHANGELOG.md, /repo/commands/bkit.md, /repo/evals/workflow/github-stats/expected-1.md and 4 more
Artifact contains critical command injection and data exfiltration risks.
The artifact includes multiple instances of critical command injection vulnerabilities, allowing shell execution via child processes and `eval` in various JavaScript files, including `/repo/evals/runner.js` and `/repo/lib/defense/push-event-guard.js`. It also exhibits high-severity data exfiltration capabilities through file system access across 231 occurrences. Additionally, the artifact contains critical findings related to skill definitions and high-severity findings indicating potential system manipulation and credential access.
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.
6 AAK-IPI-WILD-CORPUS-001
Files: CHANGELOG.md, agents/bkend-expert.md, bkit-system/scenarios/scenario-qa.md and 3 more · reported by agent-audit-kit
5 AAK-SECRET-004
Files: lib/intent/language.js, lib/i18n/detector.js, lib/qa/utils/pattern-matcher.js and 1 more · reported by agent-audit-kit
5 AAK-SKILL-003
Files: skills/phase-9-deployment/SKILL.md, skills/dynamic/SKILL.md, skills/zero-script-qa/SKILL.md and 2 more · reported by agent-audit-kit
4 COMMAND_INJECTION_EVAL
Files: /repo/evals/runner.js, /repo/lib/defense/push-event-guard.js, /repo/lib/pdca/workflow-engine.js · reported by cisco-skill-scanner
4 YARA_system_manipulation_generic
Files: /repo/.claude-plugin/marketplace.json, /repo/lib/defense/heredoc-detector.js · reported by cisco-skill-scanner
3 AAK-TASKS-003
Files: lib/team/task-queue.js, lib/team/hooks.js, lib/team/index.js · reported by agent-audit-kit
3 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/CHANGELOG.md · reported by nerlo-install-instruction
3 YARA_prompt_injection_unicode_steganography
Files: /repo/images/bkit-intro.png, /repo/images/bkit-marketplace.png, /repo/images/to-use-non-development.png · reported by cisco-skill-scanner
2 AAK-HEALTHCARE-AI-004
Files: CHANGELOG.md, bkit-system/components/scripts/_scripts-overview.md · reported by agent-audit-kit
2 AAK-LEGAL-002
Files: servers/bkit-analysis-server/package.json, servers/bkit-pdca-server/package.json · reported by agent-audit-kit
2 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
2 AAK-SKILL-004
Files: skills/skill-create/SKILL.md, skills/pdca/SKILL.md · reported by agent-audit-kit
2 EXCESSIVE_FILE_COUNT
Files: /repo/., /repo/evals/. · reported by cisco-skill-scanner
2 FILE_MAGIC_MISMATCH
Files: /repo/skills/cc-version-analysis/SKILL.md · reported by cisco-skill-scanner
2 LOW_ANALYZABILITY
Files: /repo, /repo/skill-creator · reported by cisco-skill-scanner
2 opt.nerlo-rules.nerlo-install-destructive-system-command
Files: /repo/CHANGELOG.md · reported by nerlo-install-instruction
2 PIPELINE_TAINT_FLOW
Files: /repo/CHANGELOG.md, /repo/SKILL.md · reported by cisco-skill-scanner
1 AAK-AGENT-SHARED-RES-AUTHZ-001
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
1 AAK-SKILL-001
Files: skills/mobile-app/SKILL.md · reported by agent-audit-kit
1 AAK-STATE-PRIVACY-001
Files: PRIVACY.md · reported by agent-audit-kit
1 AAK-STATE-PRIVACY-002
Files: PRIVACY.md · reported by agent-audit-kit
1 AAK-STATE-PRIVACY-003
Files: PRIVACY.md · reported by agent-audit-kit
1 MANIFEST_INVALID_NAME
Files: /repo/.claude/SKILL.md · reported by cisco-skill-scanner
1 UNANALYZABLE_BINARY
Files: /repo/bkit-infra-architecture.pdf · reported by cisco-skill-scanner
1 YARA_autonomy_abuse_generic
Files: /repo/lib/core/session-title-cache.js · reported by cisco-skill-scanner
Showing 25 of 290; the rest are in the per-scanner reports above.