The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process arbitrary web content through search and scraping results, creating a surface for embedded instructions to influence agent behavior.
Ingestion points: Search results and full-page scraped content are saved to .firecrawl/*.json files for the agent to read and process (SKILL.md).
Boundary markers: The instructions do not define specific delimiters or "ignore" warnings to prevent the agent from obeying instructions hidden within the scraped web data.
Capability inventory: The agent utilizes the Bash tool to execute firecrawl CLI commands and jq for data processing (SKILL.md).
Sanitization: There is no mention of sanitization, filtering, or validation of the external content before it is processed by the agent.
[COMMAND_EXECUTION]: The skill uses the Bash tool to execute the firecrawl binary and npx firecrawl-cli. These are standard command-line operations for searching, scraping, and managing credits via the Firecrawl service.
[EXTERNAL_DOWNLOADS]: The skill allows execution via npx firecrawl-cli, which involves downloading the CLI package from the public npm registry. This is a vendor-owned resource associated with the skill's author, 'firecrawl'.

firecrawl-search