firecrawl-research-index
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized commands were identified. The skill instructions are consistent with its stated purpose of researching scientific literature.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external research data, which presents an inherent surface for indirect prompt injection.
- Ingestion points: Untrusted data enters the context through
firecrawl_research_read_paper(passages) andfirecrawl_scrape(source URLs) mentioned inSKILL.md. - Boundary markers: The instructions do not specify technical delimiters but provide procedural instructions for the agent to distinguish synthetic analysis from original source claims.
- Capability inventory: The skill utilizes specialized research and scraping tools (
firecrawl_research_*,firecrawl_scrape). - Sanitization: No specific sanitization or filtering logic is provided for the retrieved external content.
Audit Metadata