skills/openclaw/skills/skill-search/Gen Agent Trust Hub

skill-search

Warn

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection attacks. It reads the contents of SKILL.md files from user-defined directories and presents descriptions and triggers directly to the agent. A malicious skill could embed instructions in these fields to manipulate the agent's behavior during search retrieval. \n
  • Ingestion points: scripts/embeddings.py (line 91) and scripts/skill_search.py (line 27) read skill documentation from the filesystem. \n
  • Boundary markers: Output is presented to the agent as plain text without delimiters or explicit instructions to ignore embedded commands. \n
  • Capability inventory: The tool performs file read operations across system and user paths and writes to a local JSON index. \n
  • Sanitization: Content is limited to 2000 characters, but no escaping or validation of natural language instructions is performed. \n- [PROMPT_INJECTION]: The skill uses deceptive metadata to misrepresent its capabilities. Both the SKILL.md file and script docstrings claim to provide 'LLM-powered task matching' and 'Semantic Search' using embedding models. However, the implementation in scripts/embeddings.py (line 125) uses a trivial character-level trigram hashing function. This discrepancy can lead the agent or user to over-rely on potentially inaccurate or manipulated search results.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 13, 2026, 07:04 AM
Security Audit — agent-trust-hub — skill-search