firecrawl-knowledge-ingest
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest content from external websites and documentation portals, creating a surface where malicious instructions could be embedded in the source data.
- Ingestion points: External article content scraped as markdown, metadata (titles, tags, author), and sidebar navigation links (referenced in SKILL.md under the 'Firecrawl Collection Plan' section).
- Boundary markers: The instructions define a specific 'Final Deliverable' markdown structure, but do not include explicit delimiters or 'ignore' instructions for the agent to apply when processing content from potentially untrusted documentation sites.
- Capability inventory: The skill generates markdown/JSON deliverables and displays extracted content within the agent's context.
- Sanitization: No sanitization or filtering of the scraped content is described in the skill instructions.
Audit Metadata