The Agent Skills Directory

[EXTERNAL_DOWNLOADS] (MEDIUM): The skill requires the installation of the firecrawl-cli npm package. Since the package is from a third-party source not included in the pre-approved trusted repositories list, it is flagged as MEDIUM.
[COMMAND_EXECUTION] (LOW): The skill relies on executing shell commands with the firecrawl utility. It provides safety instructions, such as quoting URLs, to prevent command injection.
[CREDENTIALS_UNSAFE] (LOW): The skill includes instructions for managing authentication via firecrawl login. No hardcoded API keys or secrets were found in the provided files.
[PROMPT_INJECTION] (LOW): Category 8: Indirect Prompt Injection risk from web ingestion. Evidence: (1) Ingestion points: Search and scraping commands that download external web content. (2) Boundary markers: The skill mandates using the -o flag to write output to the .firecrawl/ directory, keeping it isolated from the primary LLM context. (3) Capability inventory: Subprocess execution of the CLI and file system writes. (4) Sanitization: Includes instructions to use grep or head for incremental reading to limit exposure to potentially malicious instructions embedded in web content.

firecrawl