web-search
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes the
websearchcommand-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
extractandsearch --contentcommands inSKILL.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
websearchCLI. - Sanitization: Content is converted to markdown without specific filtering for malicious linguistic patterns or agent-directed instructions.
Audit Metadata