web-search

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions involve the use of the 'infsh' CLI for searching and extracting data. This is the core functionality intended by the author.
  • [EXTERNAL_DOWNLOADS]: The documentation includes a reference to a GitHub URL containing setup instructions for the required CLI tool. This resource belongs to the vendor's repository.
  • [PROMPT_INJECTION]: The skill retrieves data from the web, creating an indirect prompt injection surface where external content is ingested into the agent's context.
  • Ingestion points: Results from 'tavily/search-assistant' and text extracted from URLs via 'tavily/extract' or 'exa/extract'.
  • Boundary markers: There are no specific instructions or delimiters used to isolate retrieved web content from the agent's system instructions.
  • Capability inventory: The skill utilizes the 'infsh' tool to interact with various web-based search and LLM applications.
  • Sanitization: The instructions do not specify any validation or sanitization steps for the data fetched from the internet.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 09:33 PM
Security Audit — agent-trust-hub — web-search