component-gallery

Fail

Audited by Gen Agent Trust Hub on Nov 1, 2026

Risk Level: CRITICALCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: Automated reputation scanners flagged references/index.json and references/design-system-index.md as malicious (FileRepMalware). This suggests the inclusion of files that have been pre-identified as suspicious by security software.
  • [COMMAND_EXECUTION]: The skill invokes local command-line tools firecrawl and rlama via subprocess.run in scripts/ingest.py to manage data ingestion and RAG database operations.
  • [COMMAND_EXECUTION]: In scripts/query.py, the skill executes an external Python script (rlama_retrieve.py) located in a different skill's directory (~/.claude/skills/rlama/) using subprocess.run.
  • [EXTERNAL_DOWNLOADS]: scripts/ingest.py downloads content from an unverified third-party GitHub repository (inbn/component-gallery), while scripts/fetch_mesh3d.py fetches directory listings from mesh3d.gallery.
  • [INDIRECT_PROMPT_INJECTION]: The skill's RAG system ingests untrusted markdown data from the web and third-party repositories. This content is stored and later provided to the agent, creating a vector for indirect prompt injection as there are no visible sanitization steps or boundary markers.
  • Ingestion points: scripts/ingest.py (GitHub fetch and crawl) and scripts/fetch_mesh3d.py (web fetch).
  • Capability inventory: Shell command execution via subprocess.run and network communication via urllib.request.
  • Sanitization: No sanitization or escaping of the ingested markdown content is present in the provided scripts.
  • [DYNAMIC_EXECUTION]: The scripts/query.py script dynamically builds and executes a command that invokes a script from an external skill path, which introduces a dependency on the integrity of code not directly managed by this skill.
Recommendations
  • CRITICAL: 2 file(s) identified as malware by FileRep - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 1, 2026, 10:13 AM