firecrawl-company-directories
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary purpose is to ingest and process untrusted content from external websites such as YC, Crunchbase, and Product Hunt. This creates a surface for indirect prompt injection where malicious instructions embedded in scraped web pages could attempt to influence the agent's behavior.
- Ingestion points: Web content retrieved via Firecrawl from arbitrary directory URLs.
- Boundary markers: The instructions do not define explicit delimiters or instructions to ignore embedded commands within the scraped content.
- Capability inventory: The skill is capable of scraping URLs and formatting data into JSON/CSV/Markdown.
- Sanitization: While the skill enforces a specific JSON schema for extracted fields, it does not explicitly mention sanitization of the text values retrieved from external sources.
Audit Metadata