firecrawl-prod-checklist
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides a set of instructions for a production readiness audit. It explicitly advises against insecure practices like printing or hardcoding API keys and recommends secret-managed identity rotation.
- [EXTERNAL_DOWNLOADS]: The skill references official Firecrawl documentation and GitHub repositories in references/official-docs.md. These are standard resources for the service described and do not involve remote code execution patterns.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow to ingest untrusted data from repository files using the Read, Glob, and Grep tools. * Ingestion points: Files within the target repository path and release references provided by the user. * Boundary markers: None provided in instructions to isolate data from commands. * Capability inventory: Write and Edit tools are enabled for configuration changes. * Sanitization: None described for external content. This creates a surface for indirect prompt injection where instructions embedded in project files could be misinterpreted as task commands by the agent during the audit.
Audit Metadata