firecrawl-market-research
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to search and scrape external web pages, which introduces a vulnerability surface where malicious instructions embedded in web content could influence the agent.
- Ingestion points: Web data is ingested from external market reports, news, investor relations, SEC filings, and company pages via Firecrawl search and scrape functions within
SKILL.md. - Boundary markers: There are no boundary markers or instructions to isolate or treat ingested content as untrusted data.
- Capability inventory: Uses parallel sub-agents or task runners to process text and validate sources.
- Sanitization: No explicit sanitization or filtering rules are applied to the scraped web text before it is handled by the agent.
Audit Metadata