structured-extraction
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Instructs the agent to use the bashExec tool with the jq utility to merge JSON data files retrieved from web sources.
- [PROMPT_INJECTION]: The skill's function involves ingesting data from untrusted external websites, which introduces a potential surface for indirect prompt injection. Ingestion points: Web content retrieved via scrape and search tools as described in SKILL.md. Boundary markers: The instructions do not specify the use of delimiters for processing scraped content. Capability inventory: Utilizes bashExec for file manipulation and data processing (SKILL.md). Sanitization: No specific content sanitization steps are outlined prior to processing scraped data.
Audit Metadata