firecrawl-deep-research
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill's primary function involves processing external web content, which creates a surface for indirect prompt injection.
- Ingestion points: Retrieves content from 5 to 25+ external URLs via the Firecrawl search and scrape plan in SKILL.md.
- Boundary markers: Does not implement explicit structural delimiters or specialized instructions to prevent the agent from following commands embedded in the scraped content.
- Capability inventory: Utilizes search and scraping tools and describes the use of sub-agents for information synthesis.
- Sanitization: Content is synthesized directly from source scrapes without specialized filtering or escaping of retrieved text.
Audit Metadata