Loading the registry…
An industrial-grade 'Vibe Coding' standard library and context manager for AI coding agents.
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.
65 critical findings reported by cisco-skill-scanner, agent-audit-kit, 51 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
This artifact ships from 2 sources and their verdicts differ. The worst is github (Flagged). Installing from a cleaner source does not mean the others are safe — check the source you actually install from.
github: https://github.com/kotades/kota-skillz, 509 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- kota-skillz
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
6 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
471 findings · 33.6s
v0.3.74
22 findings · 15.0s
v0.1.0
13 findings · 9.2s
v0.1.0
3 findings · 9.2s
v0.1.0
0 findings · 23.4s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.2s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image.
2 scans on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Sep 3, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source: complete | rejected |
| Aug 11, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·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 509 findings across every scanner that examined this package. 14 of 65 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.
86 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, FILE_MAGIC_MISMATCH, DATA_EXFIL_JS_FS_ACCESS · Files: /repo/skills/ponytail/tests/hermes-plugin.test.js, /repo/skills/ponytail/tests/hooks-windows.test.js, /repo/skills/ponytail/tests/hooks.test.js and 7 more · reported by cisco-skill-scanner
11 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE, MANIFEST_INVALID_NAME · Files: /repo/skills/ponytail/.github/SKILL.md, /repo/skills/ponytail/docs/SKILL.md, /repo/skills/ponytail/examples/SKILL.md and 2 more · reported by cisco-skill-scanner
2 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 · Files: skills/ponytail/AGENTS.md, skills/ponytail/.github/copilot-instructions.md · reported by 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-MARKETPLACE-001 · Files: skills/ponytail/.github/plugin/marketplace.json · 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.
96 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/skills/ponytail/.opencode/plugins/ponytail.mjs, /repo/skills/ponytail/benchmarks/arms/caveman.js, /repo/skills/ponytail/benchmarks/arms/ponytail.js and 21 more · reported by cisco-skill-scanner
63 MANIFEST_MISSING_LICENSE
Files: /repo/SKILL.md, /repo/skills/remotion-best-practices/SKILL.md, /repo/skills/ponytail/SKILL.md and 60 more · reported by cisco-skill-scanner
48 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/skills/ui-ux-pro-max-skill/SKILL.md, /repo/prompts/SKILL.md, /repo/features/SKILL.md and 45 more · reported by cisco-skill-scanner
43 HIDDEN_DATA_FILE
Files: /repo/skills/ponytail/.agents/rules/ponytail.md, /repo/skills/ponytail/.openclaw/skills/ponytail-help/SKILL.md, /repo/skills/ponytail/.windsurf/rules/ponytail.md and 20 more · reported by cisco-skill-scanner
26 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/skills/ponytail/benchmarks/correctness.js, /repo/skills/ponytail/benchmarks/robustness-audit.js, /repo/skills/ui-ux-pro-max-skill/.claude/skills/brand/scripts/sync-brand-to-tokens.cjs and 2 more
Artifact allows shell execution and credential access
The artifact contains multiple instances of potential shell execution via command injection in JavaScript child processes and `eval` calls, notably in `/repo/bin/kota.js` and `/repo/skills/ponytail/benchmarks/correctness.js`. It also exhibits capabilities for dynamic code execution and network egress of secrets from both JavaScript and Python components. A critical finding related to sensitive operations is present in `skills/ponytail/benchmarks/agentic/tasks.py`.
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.
24 COMMAND_INJECTION_EVAL
Files: /repo/skills/ponytail/benchmarks/correctness.js, /repo/skills/ponytail/benchmarks/robustness-audit.js · reported by cisco-skill-scanner
22 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/skills/ponytail/benchmarks/agentic/judge.py, /repo/skills/ponytail/benchmarks/agentic/tasks.py, /repo/skills/ponytail/benchmarks/benchmark-local.py · reported by cisco-skill-scanner
18 DATA_EXFIL_JS_NETWORK
Files: /repo/skills/ponytail/benchmarks/claude-email.js, /repo/skills/ponytail/benchmarks/model-email.js, /repo/skills/ponytail/benchmarks/robustness-audit.js and 1 more · reported by cisco-skill-scanner
9 LOW_ANALYZABILITY
Files: /repo/skeleton, /repo/skills/ponytail/benchmarks, /repo/skills/ponytail/ponytail-mcp and 6 more · reported by cisco-skill-scanner
7 AAK-HEALTHCARE-AI-004
Files: skills/ui-ux-pro-max-skill/README.md, skills/ponytail/.clinerules/ponytail.md, skills/ponytail/.openclaw/skills/ponytail/SKILL.md and 4 more · reported by agent-audit-kit
7 MANIFEST_INVALID_NAME
Files: /repo/skills/ui-ux-pro-max-skill/.claude/skills/ui-styling/SKILL.md, /repo/skills/ui-ux-pro-max-skill/.claude/skills/brand/SKILL.md, /repo/skills/ui-ux-pro-max-skill/.claude/skills/design/SKILL.md and 4 more · reported by cisco-skill-scanner
5 FILE_MAGIC_MISMATCH
Files: /repo/skills/ui-ux-pro-max-skill/cli/assets/data/react-performance.csv, /repo/skills/ui-ux-pro-max-skill/src/ui-ux-pro-max/data/react-performance.csv · reported by cisco-skill-scanner
5 opt.nerlo-rules.nerlo-hardcoded-external-egress
Files: /repo/skills/ponytail/benchmarks/claude-email.js, /repo/skills/ponytail/benchmarks/model-email.js, /repo/skills/ponytail/benchmarks/robustness-audit.js and 1 more · reported by nerlo-behavioral
4 opt.nerlo-rules.nerlo-dynamic-exec
Files: /repo/skills/ponytail/benchmarks/correctness.js, /repo/skills/ponytail/benchmarks/robustness-audit.js, /repo/skills/ui-ux-pro-max-skill/.claude/skills/brand/scripts/sync-brand-to-tokens.cjs · reported by nerlo-behavioral
3 AAK-IPI-WILD-CORPUS-001
Files: skills/supabase-postgres-best-practices/references/security-privileges.md, skills/supabase-postgres-best-practices/references/schema-partitioning.md, skills/ponytail/benchmarks/arms/caveman-SKILL.md · reported by agent-audit-kit
3 AAK-MARKETPLACE-001
Files: skills/ponytail/.claude-plugin/marketplace.json, skills/ponytail/.agents/plugins/marketplace.json, skills/ui-ux-pro-max-skill/.claude-plugin/marketplace.json · reported by agent-audit-kit
3 BINARY_FILE_DETECTED
Files: /repo/skills/ui-ux-pro-max-skill/.claude/skills/ui-styling/scripts/.coverage · reported by cisco-skill-scanner
3 EXCESSIVE_FILE_COUNT
Files: /repo/skills/ui-ux-pro-max-skill/., /repo/skills/ponytail/., /repo/. · reported by cisco-skill-scanner
3 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/skills/ponytail/benchmarks/claude-email.js, /repo/skills/ponytail/benchmarks/model-email.js, /repo/skills/ponytail/benchmarks/robustness-audit.js · reported by nerlo-behavioral
3 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/repo/SKILL.md, /repo/skills/ponytail/repo/skills/ponytail/SKILL.md, /repo/skills/ponytail/benchmarks/repo/skills/ponytail/benchmarks/README.md · reported by cisco-skill-scanner
3 UNANALYZABLE_BINARY
Files: /repo/skills/ui-ux-pro-max-skill/.claude/skills/ui-styling/scripts/.coverage · reported by cisco-skill-scanner
2 AAK-TASKS-003
Files: skills/ui-ux-pro-max-skill/src/ui-ux-pro-max/data/_sync_all.py, skills/ui-ux-pro-max-skill/cli/assets/data/_sync_all.py · reported by agent-audit-kit
2 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/skills/ponytail/benchmarks/agentic/complete.py, /repo/skills/ponytail/benchmarks/agentic/judge.py · reported by nerlo-install-instruction
1 AAK-LEGAL-002
Files: skills/ponytail/pi-extension/package.json · reported by agent-audit-kit
1 AAK-MARKETPLACE-004
Files: skills/ponytail/.agents/plugins/marketplace.json · reported by agent-audit-kit
1 AAK-MCP-015
Files: skills/ponytail/benchmarks/agentic/tasks.py · reported by agent-audit-kit
1 AAK-MCP-018
Files: skills/ponytail/ponytail-mcp/index.js · reported by agent-audit-kit
1 opt.nerlo-rules.nerlo-install-shell-inline-command
Files: /repo/skills/ui-ux-pro-max-skill/cli/src/utils/extract.ts · reported by nerlo-install-instruction
1 opt.nerlo-rules.nerlo-py-secret-to-network-egress
Files: /repo/skills/ponytail/benchmarks/agentic/judge.py · reported by nerlo-behavioral
1 PROMPT_INJECTION_IGNORE_INSTRUCTIONS
Files: /repo/instructions/SKILL.md · reported by cisco-skill-scanner
Showing 25 of 67; the rest are in the per-scanner reports above.