The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests content from external websites, creating a surface for indirect prompt injection where malicious instructions embedded in web pages could attempt to influence the agent's behavior.
Ingestion points: Website content extracted via the firecrawl_crawl MCP tool or the firecrawl CLI.
Boundary markers: The instructions do not specify explicit delimiters or "ignore instructions" markers for the ingested content.
Capability inventory: The skill can write output to local files (e.g., .firecrawl/crawl.json) and execute CLI commands via the Bash tool.
Sanitization: No specific sanitization or filtering logic is defined for the external content before it enters the agent's context.
[COMMAND_EXECUTION]: The skill uses the Bash tool to execute firecrawl CLI commands for crawling and checking job status. These commands are scoped to the firecrawl namespace.
[EXTERNAL_DOWNLOADS]: The skill documentation suggests using npx firecrawl, which involves downloading and executing the firecrawl package from the npm registry. As this is a tool provided by the skill's author, it is a legitimate resource for this skill's functionality.

firecrawl-crawl