firecrawl-qa
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external websites during QA testing and scraping tasks.
- Ingestion points: Firecrawl map, browser, and scrape tools extract content from user-provided target URLs.
- Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious content embedded in the target sites.
- Capability inventory: The agent uses Firecrawl tools to browse, map, and scrape, and then generates structured reports based on this data.
- Sanitization: No explicit sanitization or filtering of the external website content is described in the skill instructions.
Audit Metadata