firecrawl-research-index
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data from research paper abstracts and full-text passages, which creates a potential surface for indirect prompt injection.
- Ingestion points: External data enters the agent context via the
firecrawl_research_read_papertool (extracting in-body passages) and thefirecrawl_scrapetool (fetching web content from the general web). - Boundary markers: The instructions do not specify the use of delimiters (like XML tags) or instructions to ignore embedded directives within the retrieved papers.
- Capability inventory: The skill provides access to search and retrieval tools (
firecrawl_research_*,firecrawl_search,firecrawl_scrape). No capabilities for arbitrary code execution, system-level file writes, or privilege escalation were identified. - Sanitization: There are no instructions or built-in mechanisms described for sanitizing or escaping the content retrieved from research papers before it is processed by the agent.
Audit Metadata