firecrawl-enterprise-rbac
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external documentation links and local configuration files, which presents a surface for indirect prompt injection.\n
- Ingestion points: Reads local code, configuration, tests, and external documentation links specified in
references/official-docs.md.\n - Boundary markers: The instructions do not define explicit delimiters or instructions to ignore embedded commands in the processed data.\n
- Capability inventory: The skill uses
Read,Glob,Grep,Write, andEdittools to perform its tasks.\n - Sanitization: There are no explicit sanitization steps mentioned for the ingested data.\n- [EXTERNAL_DOWNLOADS]: The skill references multiple external URLs for official Firecrawl documentation and source code.\n
- Evidence: Links to
docs.firecrawl.devandgithub.com/firecrawlare provided inreferences/official-docs.md.\n - Note: These references target the official documentation and repositories of the well-known service the skill is designed to govern.
Audit Metadata