firecrawl-research-index

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process text from external research paper abstracts and full-text bodies, which are untrusted external sources.
  • Ingestion points: Content enters the agent context via the firecrawl_research_search_papers, firecrawl_research_inspect_paper, and firecrawl_research_read_paper tools as specified in SKILL.md.
  • Boundary markers: There are no explicit instructions or delimiters defined to separate the fetched paper content from the agent's core instructions, making it theoretically possible for a paper to influence agent behavior.
  • Capability inventory: The agent has the capability to search, inspect canonical metadata, and read specific passages from the external research corpus.
  • Sanitization: The instructions do not define any sanitization, filtering, or validation processes for the data retrieved from the research index.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 10:50 AM
Security Audit — agent-trust-hub — firecrawl-research-index