web-search

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes the websearch command-line utility to interact with search APIs and extract content from URLs.
  • [PROMPT_INJECTION]: This skill presents a risk of indirect prompt injection.
  • Ingestion points: Web content is ingested into the agent context through the extract and search --content commands in SKILL.md.
  • Boundary markers: No delimiters or warnings are provided to prevent the agent from following instructions embedded in the retrieved web data.
  • Capability inventory: The skill enables subprocess execution of the websearch CLI.
  • Sanitization: Content is converted to markdown without specific filtering for malicious linguistic patterns or agent-directed instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 05:41 PM