firecrawl-company-directories
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from untrusted external directories such as Crunchbase or YC, which could contain hidden instructions targeting the agent.
- Ingestion points: External web content scraped from user-specified directories (SKILL.md).
- Boundary markers: Absent; the instructions do not include specific delimiters or warnings to ignore embedded instructions in the scraped data.
- Capability inventory: The skill utilizes the Firecrawl API for automated web scraping and data extraction.
- Sanitization: Absent; there is no evidence of content filtering or escaping before the data is processed into the final deliverable.
Audit Metadata