The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or dangerous commands were detected in the skill file.
[DATA_EXPOSURE]: The skill requires a FIRECRAWL_API_KEY to be provided as an input. Requesting credentials via standard input fields is considered a safe and recommended practice for managing service access.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process content from external websites (company directories), which is an inherent part of its functionality. Ingestion points: Data is fetched from external directory URLs provided at runtime. Boundary markers: No explicit delimiting or instructions to ignore embedded commands are present in the extraction template. Capability inventory: No executable scripts, shell commands, or network writing capabilities are included in this skill file. Sanitization: No explicit sanitization or filtering logic is defined for the external content.

firecrawl-company-directories