firecrawl-local-dev-loop
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for creating deterministic development environments and local testing patterns for Firecrawl integrations.
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill explicitly instructs against printing, committing, or transmitting API keys and recommends using approved secret managers for authentication.
- [EXTERNAL_DOWNLOADS]: The skill references official Firecrawl documentation and GitHub repositories for implementation details, which is consistent with its stated purpose of facilitating local development.
- [INDIRECT_PROMPT_INJECTION]: The skill processes repository code and configuration as input, which constitutes an ingestion point for potentially untrusted data.
- Ingestion points: Target repository code, integration paths, and configuration files (SKILL.md).
- Boundary markers: Includes instructions to define typed adapter interfaces and wrapper boundaries to isolate external behavior.
- Capability inventory: Limited to file system operations via Read, Glob, Grep, Write, and Edit tools (SKILL.md).
- Sanitization: Focuses on creating synthetic fixtures and unit tests to avoid processing live production payloads.
Audit Metadata