firecrawl-research-index
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external research paper databases and web sources, creating an attack surface where malicious instructions could be embedded in the retrieved content.
- Ingestion points: Tools such as
firecrawl_research_search_papers,firecrawl_research_read_paper,firecrawl_search, andfirecrawl_scrapeingest external abstracts, paper bodies, and web pages into the agent's context. - Boundary markers: The skill does not provide instructions to the agent to treat retrieved content as data-only or to ignore embedded instructions within the results.
- Capability inventory: The skill provides extensive tools for network-based data retrieval and scraping, which are used to populate the agent's context with external information.
- Sanitization: No sanitization or validation of the content retrieved from external sources is described in the skill's operational logic.
Audit Metadata