Firecrawler
Analysis
Firecrawler is a coherent Firecrawl API helper, with expected notes around its API key, third-party provider use, and unpinned SDK install.
Findings (4)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
pip3 install firecrawl
The setup installs an unpinned third-party SDK. This is expected for a Firecrawl integration, but the artifacts do not pin a version or provide a lockfile.
python3 fc.py crawl "https://docs.example.com" --limit 50 --output ./docs
The skill can crawl many pages through Firecrawl. This is central to the stated purpose and the documentation warns about credits, but users should keep limits reasonable.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
export FIRECRAWL_API_KEY=fc-your-key-here
The skill requires a Firecrawl API key, while the registry metadata says there is no primary credential or required environment variable. This is disclosed and purpose-aligned, but it gives the skill access to the user's Firecrawl account credits.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
return Firecrawl(api_key=api_key)
The script uses Firecrawl as an external provider for URLs, searches, screenshots, and extraction requests. This is disclosed by the skill purpose, but user-supplied URLs, queries, schemas, and prompts may be processed by that provider.
