firecrawl-knowledge-base
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted external data, which creates an attack surface for indirect prompt injection.
- Ingestion points: Data enters the agent's context from arbitrary web sources using Firecrawl's map, search, and scrape tools (SKILL.md).
- Boundary markers: The instructions lack markers or specific warnings to the agent to ignore or delimit potentially malicious instructions found within the scraped content.
- Capability inventory: The skill leverages capabilities to write the collected and processed data into various markdown and JSON file formats in a local directory.
- Sanitization: No sanitization, filtering, or validation steps are defined to process the external content before it is stored or used in RAG contexts.
Audit Metadata