firecrawl-knowledge-ingest
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the processing of untrusted external content from documentation portals.
- Ingestion points: The skill ingests data from external URLs defined or inferred during the onboarding interview (SKILL.md).
- Boundary markers: The instructions do not specify any boundary markers or instructions for the agent to ignore embedded commands within the extracted documentation content.
- Capability inventory: The skill uses the Firecrawl browser to crawl websites, identify navigation, and extract article content as markdown or JSON.
- Sanitization: There is no explicit sanitization or validation of the ingested content to prevent malicious instructions within the documentation from influencing the agent.
Audit Metadata