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.
5 critical findings reported by 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 -- @xberg-io/plugins
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- @xberg-io/plugins ~/.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 · 0.5s
v2.0.11
727 findings · 20.5s
v0.3.74
44 findings · 5.2s
v0.1.0
0 findings · 4.5s
v0.1.0
1 finding · 4.5s
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 · 1.9s
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 ·n/a: not applicable | 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 777 findings across every scanner that examined this package. None of the 5 findings rated critical by their scanner were dismissed.
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.
8 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, AAK-GHA-IMMUTABLE-001 · Files: .github/plugin/marketplace.json, .github/workflows/publish.yaml · reported by agent-audit-kit
2 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 · Files: /repo/docs/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.
468 HIDDEN_DATA_FILE
Files: /repo/.ai-rulez/config.toml, /repo/plugins/liter-llm/.ai-rulez/config.toml, /repo/plugins/crawlberg/.ai-rulez/config.toml and 233 more · reported by cisco-skill-scanner
161 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/liter-llm/.ai-rulez/skills/running-the-proxy/SKILL.md, /repo/plugins/liter-llm/.ai-rulez/skills/embeddings-and-search/SKILL.md, /repo/plugins/liter-llm/.ai-rulez/skills/tool-calling/SKILL.md and 158 more · reported by cisco-skill-scanner
60 HIDDEN_EXECUTABLE_SCRIPT
Files: /repo/plugins/liter-llm/.ai-rulez/opencode/index.js, /repo/plugins/crawlberg/.ai-rulez/opencode/index.js, /repo/plugins/html-to-markdown/.ai-rulez/opencode/index.js and 27 more · reported by cisco-skill-scanner
16 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/plugins/liter-llm/SKILL.md, /repo/plugins/crawlberg/SKILL.md and 13 more · reported by cisco-skill-scanner
10 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json, .agents/plugins/marketplace.json
Critical findings present; artifact includes executable scripts and marketplace interactions.
The artifact contains critical findings related to multiple plugin configurations, specifically in files like `plugins/crawlberg/.claude-plugin/mcp.json`. It also includes numerous hidden executable scripts, such as `index.js` and `__init__.py` files within various plugin directories, which could allow shell execution. Further high-severity findings indicate the presence of compound extract and execute capabilities, and interactions with marketplace configurations.
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.
10 AAK-MCP-006
Files: plugins/liter-llm/.mcp.json, plugins/crawlberg/.mcp.json, plugins/html-to-markdown/.mcp.json and 7 more · reported by agent-audit-kit
10 AAK-MCP-ATTEST-001
Files: plugins/liter-llm/.mcp.json, plugins/crawlberg/.mcp.json, plugins/html-to-markdown/.mcp.json and 7 more · reported by agent-audit-kit
10 COMPOUND_EXTRACT_EXECUTE
Files: /repo/plugins/crawlberg/scripts/mcp-launch.sh, /repo/plugins/html-to-markdown/scripts/mcp-launch.sh, /repo/plugins/liter-llm/scripts/mcp-launch.sh and 2 more · reported by cisco-skill-scanner
8 FILE_MAGIC_MISMATCH
Files: /repo/plugins/html-to-markdown/.hermes/package/src/html_to_markdown_hermes_plugin/plugin.yaml, /repo/plugins/html-to-markdown/.hermes/plugins/html-to-markdown/plugin.yaml, /repo/plugins/liter-llm/.hermes/package/src/liter_llm_hermes_plugin/plugin.yaml and 1 more · reported by cisco-skill-scanner
5 AAK-MCP-002
Files: plugins/liter-llm/.claude-plugin/mcp.json, plugins/crawlberg/.claude-plugin/mcp.json, plugins/html-to-markdown/.claude-plugin/mcp.json and 2 more · reported by agent-audit-kit
2 EXCESSIVE_FILE_COUNT
Files: /repo/., /repo/plugins/xberg/. · reported by cisco-skill-scanner
1 AAK-LEGAL-002
Files: package.json · reported by agent-audit-kit
1 mcp-no-desc-crawlberg
Files: plugins/crawlberg/.claude-plugin/mcp.json · reported by agentshield
1 mcp-no-desc-html-to-markdown
Files: plugins/html-to-markdown/.claude-plugin/mcp.json · reported by agentshield
1 mcp-no-desc-liter-llm
Files: plugins/liter-llm/.claude-plugin/mcp.json · reported by agentshield
1 mcp-no-desc-tree-sitter-language-pack
Files: plugins/tree-sitter-language-pack/.claude-plugin/mcp.json · reported by agentshield
1 mcp-no-desc-xberg
Files: plugins/xberg/.claude-plugin/mcp.json · reported by agentshield
1 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/CONTRIBUTING.md · reported by nerlo-install-instruction
Showing 25 of 85; the rest are in the per-scanner reports above.