Loading the registry…
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.
76 critical findings reported by cisco-skill-scanner, agent-audit-kit. 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 -- 'itsphurin/dotfiles (api-doc-site)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'itsphurin/dotfiles (api-doc-site)' ~/.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
Incomplete run
0 findings · 0.6s
v2.0.11
253 findings · 91.4s
v0.3.74
12 findings · 93.0s
v0.1.0
1 finding · 24.6s
v0.1.0
5 findings · 24.6s
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 ·!: incompletecisco-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 271 findings across every scanner that examined this package. None of the 76 findings rated critical by their scanner were dismissed.
Not reviewed is not the same as clean. Those 3 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.
13 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_unicode_steganography, AAK-HEALTHCARE-AI-004, SOCIAL_ENG_VAGUE_DESCRIPTION and 1 more · Files: /repo/.github/assets/workflow-screenshot.gif, /repo/.github/assets/transparent-showcase.png, docs/superpowers/plans/2026-03-21-agent-skills.md and 2 more · reported by cisco-skill-scanner, 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.
52 COMMAND_INJECTION_EVAL
Files: /repo/config/ags.v1/@girs/astalio-0.1.d.ts, /repo/config/ags.v1/@girs/gdkwayland-4.0.d.ts, /repo/config/ags.v1/@girs/gdkx11-3.0.d.ts and 17 more · reported by cisco-skill-scanner
42 YARA_capability_inflation_generic
Files: /repo/config/ags.v1/@girs/gtk-2.0.d.ts, /repo/config/ags.v1/@girs/gtk-3.0.d.ts · reported by cisco-skill-scanner
28 FILE_MAGIC_MISMATCH
Files: /repo/arch/pkgs/snap/snaplist.txt, /repo/arch/pkgs/flatpak/flatpaklist.txt, /repo/config/pipewire/minimal.conf and 12 more · reported by cisco-skill-scanner
25 DATA_EXFIL_JS_NETWORK
Files: /repo/config/ags.v1/@girs/glib-2.0.d.ts, /repo/config/ags.v1/@girs/govirt-1.0.d.ts, /repo/config/ags.v1/@girs/webkit-6.0.d.ts and 6 more · reported by cisco-skill-scanner
25 HIDDEN_EXECUTABLE_SCRIPT
Files: /repo/config/ags.v1/modules/.configuration/user_options.js, /repo/config/ags.v1/modules/.miscutils/mathfuncs.js, /repo/config/ags.v1/modules/.commondata/quotes.js and 22 more
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/arch/.xprofile.example, /repo/.mcp.json.example · reported by cisco-skill-scanner
Critical command injection and potential remote code execution detected.
The artifact contains numerous instances of command injection and coercive injection, primarily within configuration files, which could lead to shell execution. It also exhibits potential for remote code execution and insecure trust boundaries. Additionally, there are indications of hidden executable scripts and dynamic execution capabilities.
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.
21 YARA_coercive_injection_generic
Files: /repo/config/ags.v1/@girs/gdk-2.0.d.ts, /repo/config/ags.v1/@girs/gdk-3.0.d.ts, /repo/config/ags.v1/@girs/gdk-4.0.d.ts and 13 more · reported by cisco-skill-scanner
13 MANIFEST_MISSING_LICENSE
Files: /repo/.claude/skills/setup-chrome-mcp/SKILL.md, /repo/.claude/skills/commit/SKILL.md, /repo/.claude/skills/api-doc-site/SKILL.md and 10 more · reported by cisco-skill-scanner
10 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/.claude/skills/api-doc-site/SKILL.md, /repo/SKILL.md, /repo/arch/SKILL.md and 7 more · reported by cisco-skill-scanner
8 HIDDEN_DATA_FILE
Files: /repo/config/pipewire/pipewire.conf.d/.sink-virtual-surround-7.1-hesuvi.conf.bak, /repo/arch/pkgs/.README.md.bak, /repo/.gitconfig and 2 more · reported by cisco-skill-scanner
4 AAK-TASKS-003
Files: config/ags.v1/@girs/spiceclientglib-2.0.d.ts, config/ags.v1/@girs/vulkan-1.0.d.ts, config/ags.v1/modules/.configuration/user_options.js and 1 more · reported by agent-audit-kit
4 BINARY_FILE_DETECTED
Files: /repo/config/pipewire/hrir_hesuvi/atmos.wav, /repo/config/pipewire/hrtf-sofa/hrtf_b_nh724.sofa · reported by cisco-skill-scanner
4 UNANALYZABLE_BINARY
Files: /repo/config/pipewire/hrtf-sofa/hrtf_b_nh724.sofa, /repo/config/pipewire/hrir_hesuvi/atmos.wav · reported by cisco-skill-scanner
3 AAK-SECRET-004
Files: config/ags.v1/services/gpt.js, config/ags.v1/services/gemini.js · reported by agent-audit-kit
3 opt.nerlo-rules.nerlo-install-destructive-system-command
Files: /repo/arch/README.md · reported by nerlo-install-instruction
2 AAK-LLM-SQL-RCE-001
Files: config/ags.v1/@girs/ostree-1.0.d.ts, config/ags.v1/@girs/gcrui-3.d.ts · reported by agent-audit-kit
2 LOW_ANALYZABILITY
Files: /repo, /repo/config/pipewire · reported by cisco-skill-scanner
2 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/bun/setup.zsh, /repo/starship/setup.zsh · reported by nerlo-install-instruction
2 OVERSIZED_FILE
Files: /repo/config/pipewire/hrtf-sofa/ClubFritz11.sofa · reported by cisco-skill-scanner
1 AAK-OAUTH-008
Files: config/ags.v1/@girs/gstrtsp-1.0.d.ts · reported by agent-audit-kit
1 AAK-TRUST-001
Files: .claude/settings.json · reported by agent-audit-kit
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-dynamic-exec
Files: /repo/config/ags.v1/modules/overview/windowcontent.js · reported by nerlo-behavioral
1 TOOL_ABUSE_SYSTEM_PACKAGE_INSTALL
Files: /repo/zsh/setup.sh · reported by cisco-skill-scanner
Showing 25 of 111; the rest are in the per-scanner reports above.