deep-research
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and synthesize large amounts of untrusted content from the open web.
- Ingestion points: Data enters the agent context through
firecrawl_search,firecrawl_scrape,web_search_exa, andcrawling_exatools mentioned inSKILL.md. - Boundary markers: The instructions do not define delimiters or specific safety warnings to prevent the agent from following instructions that might be embedded in scraped web pages.
- Capability inventory: The skill uses the
Tasktool for parallel execution and provides instructions for saving research reports to the local file system. - Sanitization: No validation or sanitization steps are defined for the content retrieved from external URLs before it is processed by the agent.
Audit Metadata