firecrawl-qa
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious intent or suspicious patterns were found in the instructions, metadata, or workflow definitions.
- [EXTERNAL_DOWNLOADS]: The skill references and interacts with the Firecrawl service (firecrawl.dev), which is a well-known platform for web scraping and data extraction.
- [PROMPT_INJECTION]: The skill ingests untrusted data from external websites as part of its core scraping functionality.
- Ingestion points: Scrapes page content and links from target URLs specified during the QA process.
- Boundary markers: The skill does not instruct the agent to use specific delimiters or protective framing when processing the scraped data.
- Capability inventory: The agent performs browser interactions, including navigation and form exploration.
- Sanitization: There is no explicit requirement for filtering or sanitizing the ingested web content before processing.
Audit Metadata