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.
28 critical findings reported by cisco-skill-scanner. 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 -- scenecraft
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- scenecraft ~/.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
25 findings · 0.9s
v2.0.11
609 findings · 28.8s
v0.3.74
21 findings · 12.9s
v0.1.0
1 finding · 6.0s
v0.1.0
8 findings · 6.1s
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 · 1.7s
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 664 findings across every scanner that examined this package. None of the 28 findings rated critical by their scanner were dismissed.
Not reviewed is not the same as clean. Those 7 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.
5 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: LOW_ANALYZABILITY, SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE · Files: /repo/forked-skills/ux-ui-agent-skills/examples/golden, /repo/forked-skills/ux-ui-agent-skills/examples/golden/SKILL.md, /repo/forked-skills/ux-ui-agent-skills/examples/sample-app/SKILL.md · reported by 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.
286 MANIFEST_MISSING_LICENSE
Files: /repo/skill/SKILL.md, /repo/.claude/skills/figma-integration/SKILL.md, /repo/.claude/skills/apply-aesthetic/SKILL.md and 283 more · reported by cisco-skill-scanner
212 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/forked-skills/skills/skills/fal-workflow/SKILL.md, /repo/SKILL.md, /repo/.claude/skills/figma-integration/workflows/SKILL.md and 209 more · reported by cisco-skill-scanner
26 HIDDEN_DATA_FILE
Files: /repo/.agents/skills/shadcn/mcp.md, /repo/.agents/skills/migrate-radix-to-base/universal-patterns.md, /repo/.agents/skills/shadcn/SKILL.md and 23 more · reported by cisco-skill-scanner
22 PATH_TRAVERSAL_ATTEMPT
Files: /repo/.claude/skills/micro-interaction/SKILL.md, /repo/.claude/skills/svg-animation/SKILL.md, /repo/.claude/skills/migrate-design-system/design-systems/SKILL.md and 19 more · reported by cisco-skill-scanner
15 AAK-HEALTHCARE-AI-004
Files: forked-skills/anthropic-skills/skills/frontend-design/SKILL.md, forked-skills/skills/skills/ugc/references/examples.md, forked-skills/ux-ui-agent-skills/design-systems/library/vercel/DESIGN.md and 12 more
The model could have called any of these a false positive and did not.
1 PATH_TRAVERSAL_ATTEMPT
Files: /repo/.claude/skills/page-transition-animation/SKILL.md · reported by cisco-skill-scanner
6 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: skills-missing-governance-forked-skills/ux-ui-agent-skills/.claude/commands/gate.md, skills-missing-governance-forked-skills/ux-ui-agent-skills/.claude/commands/scaffold-project.md, skills-missing-telemetry-forked-skills/ux-ui-agent-skills/.claude/commands/scaffold-project.md and 3 more · Files: forked-skills/ux-ui-agent-skills/.claude/commands/gate.md, forked-skills/ux-ui-agent-skills/.claude/commands/scaffold-project.md, forked-skills/ux-ui-agent-skills/.claude/commands/ship.md · reported by agentshield
1 The model did not answer for these findings.
Rules: LOW_ANALYZABILITY · Files: /repo/forked-skills/ux-ui-agent-skills/examples/sample-app · reported by cisco-skill-scanner
Artifact exhibits critical path traversal, command, and coercive injection risks.
The artifact contains critical path traversal vulnerabilities in multiple skill definitions, allowing access to arbitrary files. It also includes critical command injection via JavaScript child processes and coercive injection, enabling shell execution. High-severity findings indicate potential exposure of credentials, additional shell execution via piped commands, and dynamic Python execution. Furthermore, the artifact performs network egress, which is flagged as a medium-severity concern.
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.
15 DATA_EXFIL_JS_NETWORK
Files: /repo/forked-skills/skills/skills/fal-redesign/runtime/src/fal.mjs, /repo/forked-skills/skills/skills/fal-redesign/runtime/src/upgrade.mjs · reported by cisco-skill-scanner
10 UNANALYZABLE_BINARY
Files: /repo/public/models/gargoyle-statue-mid.glb, /repo/forked-skills/anthropic-skills/skills/web-artifacts-builder/scripts/shadcn-components.tar.gz, /repo/public/models/gargoyle-statue-low.glb and 3 more · reported by cisco-skill-scanner
8 LOW_ANALYZABILITY
Files: /repo/forked-skills/skills/skills/fal-redesign/runtime, /repo/forked-skills/skills/skills/fal-redesign, /repo/forked-skills/anthropic-skills/skills/web-artifacts-builder and 5 more · reported by cisco-skill-scanner
8 PIPELINE_TAINT_FLOW
Files: /repo/forked-skills/skills/skills/genmedia/references/full-reference.md, /repo/README.md, /repo/SKILL.md and 2 more · reported by cisco-skill-scanner
4 AAK-SECRET-004
Files: .claude/skills/design-code/scripts/lint_hardcodes.py, .claude/skills/redesign/scripts/lint_hardcodes.py, .claude/skills/design-qa/scripts/lint_hardcodes.py and 1 more · reported by agent-audit-kit
4 BINARY_FILE_DETECTED
Files: /repo/public/models/mascot-idle.glb, /repo/public/models/gargoyle-statue-mid.glb, /repo/public/models/gargoyle-statue.glb and 1 more · reported by cisco-skill-scanner
4 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/README.md, /repo/forked-skills/skills/skills/genmedia/SKILL.md, /repo/forked-skills/skills/skills/genmedia/references/full-reference.md and 1 more · reported by nerlo-install-instruction
4 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/forked-skills/anthropic-skills/skills/webapp-testing/scripts/with_server.py, /repo/forked-skills/skills/skills/fal-redesign/runtime/bin/fal-site.mjs, /repo/forked-skills/skills/skills/fal-redesign/runtime/src/upgrade.mjs and 1 more · reported by nerlo-install-instruction
4 YARA_coercive_injection_generic
Files: /repo/.claude/skills/design-code/accessibility/SKILL.md, /repo/.claude/skills/design-component/accessibility/SKILL.md, /repo/.claude/skills/a11y-audit/accessibility/SKILL.md and 1 more · reported by cisco-skill-scanner
3 ARCHIVE_FILE_DETECTED
Files: /repo/forked-skills/anthropic-skills/skills/web-artifacts-builder/scripts/shadcn-components.tar.gz · reported by cisco-skill-scanner
2 EXCESSIVE_FILE_COUNT
Files: /repo/., /repo/forked-skills/ux-ui-agent-skills/design-systems/. · reported by cisco-skill-scanner
1 AAK-LEGAL-002
Files: package.json · reported by agent-audit-kit
1 AAK-SUPPLY-005
Files: package-lock.json · reported by agent-audit-kit
1 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/forked-skills/ux-ui-agent-skills/scripts/accuracy_report.mjs · reported by cisco-skill-scanner
1 hooks-no-pretooluse
Files: forked-skills/ux-ui-agent-skills/.claude/settings.json · reported by agentshield
1 opt.nerlo-rules.nerlo-py-dynamic-exec
Files: /repo/forked-skills/anthropic-skills/skills/webapp-testing/scripts/with_server.py · reported by nerlo-behavioral
1 permissions-no-deny-list
Files: forked-skills/ux-ui-agent-skills/.claude/settings.json · reported by agentshield
1 permissions-permissive-Bash(node scripts/axe_audit.mjs:*)
Files: forked-skills/ux-ui-agent-skills/.claude/settings.json · reported by agentshield
1 permissions-permissive-Bash(node scripts/build_tokens.mjs:*)
Files: forked-skills/ux-ui-agent-skills/.claude/settings.json · reported by agentshield
1 permissions-permissive-Bash(node scripts/measure_render.mjs:*)
Files: forked-skills/ux-ui-agent-skills/.claude/settings.json · reported by agentshield
1 permissions-permissive-Bash(node scripts/taste_audit.mjs:*)
Files: forked-skills/ux-ui-agent-skills/.claude/settings.json · reported by agentshield
1 permissions-permissive-Bash(node scripts/verify_focustrap.mjs:*)
Files: forked-skills/ux-ui-agent-skills/.claude/settings.json · reported by agentshield
1 permissions-permissive-Bash(node scripts/verify_responsive.mjs:*)
Files: forked-skills/ux-ui-agent-skills/.claude/settings.json · reported by agentshield
1 permissions-permissive-Bash(node scripts/verify_rtl.mjs:*)
Files: forked-skills/ux-ui-agent-skills/.claude/settings.json · reported by agentshield
1 permissions-permissive-Bash(node scripts/verify_states.mjs:*)
Files: forked-skills/ux-ui-agent-skills/.claude/settings.json · reported by agentshield
1 permissions-permissive-Bash(python3 scripts/check_no_emoji.py:*)
Files: forked-skills/ux-ui-agent-skills/.claude/settings.json · reported by agentshield
1 permissions-permissive-Bash(python3 scripts/contrast.py:*)
Files: forked-skills/ux-ui-agent-skills/.claude/settings.json · reported by agentshield
1 permissions-permissive-Bash(python3 scripts/lint_hardcodes.py:*)
Files: forked-skills/ux-ui-agent-skills/.claude/settings.json · reported by agentshield
1 permissions-permissive-Bash(python3 scripts/lint_taste.py:*)
Files: forked-skills/ux-ui-agent-skills/.claude/settings.json · reported by agentshield
1 permissions-permissive-Bash(python3 scripts/scaffold_component.py:*)
Files: forked-skills/ux-ui-agent-skills/.claude/settings.json · reported by agentshield
1 permissions-permissive-Bash(python3 scripts/validate_component_spec.py:*)
Files: forked-skills/ux-ui-agent-skills/.claude/settings.json · reported by agentshield
1 permissions-permissive-Bash(python3 scripts/validate_contrast.py:*)
Files: forked-skills/ux-ui-agent-skills/.claude/settings.json · reported by agentshield
1 permissions-permissive-Bash(python3 scripts/validate_theme_refs.py:*)
Files: forked-skills/ux-ui-agent-skills/.claude/settings.json · reported by agentshield
1 permissions-permissive-Bash(python3 scripts/validate_tokens.py:*)
Files: forked-skills/ux-ui-agent-skills/.claude/settings.json · reported by agentshield
1 SOCIAL_ENG_ANTHROPIC_IMPERSONATION
Files: /repo/forked-skills/anthropic-skills/SKILL.md · reported by cisco-skill-scanner
Showing 25 of 61; the rest are in the per-scanner reports above.