Loading the registry…
Accessibility audit against WCAG 2.1 AA. Checks semantic HTML, ARIA, keyboard navigation, color contrast, screen reader compatibility.
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.
3 critical findings reported by cisco-skill-scanner, agent-audit-kit, 1 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 -- 'haabe/mycelium (a11y-check)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'haabe/mycelium (a11y-check)' ~/.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
5 findings · 1.0s
v2.0.11
364 findings · 44.1s
v0.3.74
19 findings · 23.2s
v0.1.0
0 findings · 6.8s
v0.1.0
31 findings · 6.8s
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 · 1.1s
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 419 findings across every scanner that examined this package. 2 of 3 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.
227 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-MARKETPLACE-001, FILE_MAGIC_MISMATCH, LOW_ANALYZABILITY and 4 more · Files: tests/bash/fixtures/check_46/good/.claude-plugin/marketplace.json, tests/bash/fixtures/check_46/bad/.claude-plugin/marketplace.json, /repo/tests/bash/fixtures/check_37/covered/tests/bash/test_check_2.sh and 111 more · reported by agent-audit-kit, cisco-skill-scanner
27 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: COMPOUND_FIND_EXEC, opt.nerlo-rules.nerlo-install-pipe-to-shell, AAK-HEALTHCARE-AI-004 and 3 more · Files: /repo/docs/SKILL.md, /repo/docs/changelog.md, /repo/docs/integrations/opencode.md and 7 more · reported by cisco-skill-scanner, nerlo-install-instruction, agent-audit-kit
3 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-AGENT-003, AAK-AGENT-002, TOOL_ABUSE_UNDECLARED_NETWORK · Files: CLAUDE.md, AGENTS.md, /repo/repo/AGENTS.md · reported by agent-audit-kit, 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.
88 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/mycelium/skills/bias-check/SKILL.md, /repo/plugins/mycelium/skills/prompt-optimizer/SKILL.md, /repo/plugins/mycelium/skills/harms-check/SKILL.md and 85 more · reported by cisco-skill-scanner
27 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/.claude/SKILL.md, /repo/.claude/diamonds/SKILL.md and 24 more · reported by cisco-skill-scanner
10 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/.claude/harness/decision-log.md, /repo/.claude/memory/cluster-instances.md, /repo/.claude/memory/corrections.md and 3 more · reported by nerlo-install-instruction
7 AAK-HEALTHCARE-AI-004
Files: .claude/canvas/opportunities.yml, .claude/harness/decision-log.md, plugins/mycelium/jit-tooling/detector.md and 4 more · reported by agent-audit-kit
6 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/plugins/mycelium/integrations/opencode/check-tool-calling.py
Critical secret exposure and high-risk capabilities detected.
The artifact contains a critical secret exposure in `.claude/evals/scenarios/delivery/security-awareness.yml` and high-severity issues including potential infinite loops in `plugins/mycelium/scripts/framework_guard.py`. It also has broad permissions for mutable tools in `settings.json` and exposes sensitive internal information in `plugins/mycelium/harness/delegation-authority.md`. Further, a high-severity secret is present in `plugins/mycelium/scripts/_manifest_lib.py` and a marketplace configuration issue exists in `.claude-plugin/marketplace.json`.
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.
3 FILE_MAGIC_MISMATCH
Files: /repo/plugins/mycelium/hooks/diamond-state-audit.sh · reported by cisco-skill-scanner
3 RESOURCE_ABUSE_INFINITE_LOOP
Files: /repo/plugins/mycelium/scripts/framework_guard.py · reported by cisco-skill-scanner
2 EXCESSIVE_FILE_COUNT
Files: /repo/plugins/mycelium/., /repo/. · reported by cisco-skill-scanner
2 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/plugins/mycelium/repo/plugins/mycelium/README.md, /repo/plugins/mycelium/integrations/opencode/repo/plugins/mycelium/integrations/opencode/README.md · reported by cisco-skill-scanner
1 AAK-IPI-WILD-CORPUS-001
Files: plugins/mycelium/harness/delegation-authority.md · reported by agent-audit-kit
1 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
1 AAK-SECRET-002
Files: .claude/evals/scenarios/delivery/security-awareness.yml · reported by agent-audit-kit
1 AAK-SECRET-004
Files: plugins/mycelium/scripts/_manifest_lib.py · 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 hooks-no-pretooluse
Files: settings.json · reported by agentshield
1 LOW_ANALYZABILITY
Files: /repo/plugins/mycelium/integrations/opencode · reported by cisco-skill-scanner
1 MANIFEST_INVALID_NAME
Files: /repo/.claude/SKILL.md · reported by cisco-skill-scanner
1 permissions-all-mutable-tools
Files: settings.json · reported by agentshield
1 permissions-missing-deny->-/dev/
Files: settings.json · reported by agentshield
1 permissions-missing-deny-chmod-777
Files: settings.json · reported by agentshield
1 permissions-missing-deny-ssh
Files: settings.json · reported by agentshield