structured-extraction
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external websites via the
scrapetool. \n - Ingestion points: Website content extracted using the
scrapetool. \n - Boundary markers: The skill does not define specific prompt delimiters for external content but instructs the agent to validate the output against a strict JSON schema. \n
- Capability inventory: The skill uses
bashExecforjqprocessing andspawnAgentsfor parallel scraping. \n - Sanitization: Requires validation of required fields, data types, and citation URLs before final output. \n- [COMMAND_EXECUTION]: The skill suggests using
bashExecwithjqto merge JSON files in the/data/directory.
Audit Metadata