Skills
skills/inference-sh/agent-skills-registry/web-search/Gen Agent Trust Hub

web-search

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by fetching and processing content from external websites.\n
  • Ingestion points: Untrusted data enters the agent's context through the tavily/search-assistant, tavily/extract, exa/search, exa/answer, and exa/extract tools (SKILL.md).\n
  • Boundary markers: The examples provided do not demonstrate the use of delimiters or specific instructions to the agent to ignore instructions embedded within the retrieved web content.\n
  • Capability inventory: The skill utilizes the infsh command-line tool for operations and describes workflows where retrieved data is piped directly into other large language models (SKILL.md).\n
  • Sanitization: There is no evidence of sanitization, filtering, or structured validation of the content extracted from external URLs before it is processed by the agent.\n- [EXTERNAL_DOWNLOADS]: The documentation suggests the installation of the infsh CLI tool via npx from the inference-sh organization repository (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 09:05 PM