firecrawl-lead-gen
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues detected. The skill is a well-formed implementation for its stated purpose of lead generation. It correctly defines input requirements for the Firecrawl API key and adheres to the developer's legitimate domain and source repositories.
- [PROMPT_INJECTION]: The skill possesses a surface for Indirect Prompt Injection because it processes data from external, untrusted web sources.
- Ingestion points: Prospect databases and web directories accessed at runtime via the Firecrawl browser.
- Boundary markers: Absent; the skill does not explicitly use delimiters to separate instructions from untrusted external data.
- Capability inventory: The skill is designed to extract fields and format them into Markdown/JSON/CSV tables.
- Sanitization: Not explicitly specified; however, the skill includes a 'Quality Bar' that instructs the agent not to bypass CAPTCHAs or access controls, which serves as a behavioral constraint.
Audit Metadata