The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to navigate and extract data from external websites, which introduces a surface for indirect prompt injection where malicious instructions on a website could influence the agent's behavior.
Ingestion points: Content is ingested from arbitrary URLs provided to the firecrawl agent command.
Boundary markers: There are no explicit instructions or delimiters mentioned to isolate web content from the agent's system instructions.
Capability inventory: The skill utilizes the Bash tool to execute commands and write output to the local file system (e.g., -o .firecrawl/pricing.json).
Sanitization: No sanitization or validation of the extracted data is described within the skill instructions before the AI processes it.
[EXTERNAL_DOWNLOADS]: The skill uses npx firecrawl-cli, which downloads the latest version of the vendor's CLI tool from the NPM registry at runtime.
[REMOTE_CODE_EXECUTION]: The use of npx to fetch and execute the firecrawl-cli tool involves remote code execution. This is a standard method for the vendor to provide its tooling and is used here to facilitate the skill's primary purpose of web extraction.

firecrawl-agent