firecrawl-research-index
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external sources such as scientific databases and general websites, creating an attack surface where embedded instructions could attempt to influence the agent's logic.
- Ingestion points: External data enters the context through
firecrawl_research_read_paper,firecrawl_scrape, andfirecrawl_search(SKILL.md). - Boundary markers: The skill lacks specific instructions for using delimiters or boundary markers to isolate untrusted external content from the system prompt (SKILL.md).
- Capability inventory: The skill is authorized to perform semantic search, paper inspection, and web scraping to fetch and process external text (SKILL.md).
- Sanitization: There are no explicit sanitization or instruction-aware filtering mechanisms described for the ingested content (SKILL.md).
Audit Metadata