The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content retrieved from the web via search and scrape tools, which could contain malicious instructions designed to influence agent behavior.
Ingestion points: Data from firecrawl search and firecrawl scrape is stored in local JSON files (e.g., .firecrawl/result.json) and then read into the agent's context.
Boundary markers: The skill instructions do not provide specific boundary markers or instructions to treat web content as untrusted.
Capability inventory: The skill has access to the Bash tool to execute firecrawl CLI and jq commands.
Sanitization: There is no explicit sanitization or validation of the content scraped from external websites.
[EXTERNAL_DOWNLOADS]: The skill utilizes npx to fetch and execute the firecrawl-cli package from the npm registry. This is a vendor-owned resource used for the skill's primary functionality.
[COMMAND_EXECUTION]: The skill executes various firecrawl CLI commands and uses jq for local data processing, which are required for searching, listing, and scraping operations.

firecrawl-search