The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process large volumes of content from external websites via the firecrawl crawl command. This content is untrusted and could potentially contain indirect prompt injection attacks meant to influence the agent's logic.
Ingestion points: Content extracted from user-provided URLs in SKILL.md.
Boundary markers: The skill does not explicitly instruct the agent to use boundary markers or delimiters when processing the crawled JSON data.
Capability inventory: The skill utilizes Bash for command execution.
Sanitization: No specific sanitization or filtering steps for the crawled content are defined within the skill instructions.
[EXTERNAL_DOWNLOADS]: The skill utilizes npx firecrawl to execute the Firecrawl CLI, which involves fetching the package from the official npm registry. Firecrawl is a well-known service for web scraping and content extraction.

firecrawl-crawl