The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes content from external websites, which creates a surface for indirect prompt injection attacks.
Ingestion points: Search result excerpts and full-page scraped content managed via .firecrawl/ JSON files.
Boundary markers: The skill does not provide specific delimiters or instructions for the agent to ignore embedded instructions in the ingested content.
Capability inventory: The skill utilizes shell execution via Bash for search and scraping commands.
Sanitization: No explicit sanitization or filtering of the external content is mentioned.
[EXTERNAL_DOWNLOADS]: The skill uses npx firecrawl-cli to download and execute the vendor's command-line interface from the NPM registry. This is a legitimate and expected behavior for accessing the Firecrawl service.
[COMMAND_EXECUTION]: The skill utilizes bash commands including firecrawl, npx, and jq to interact with the search API, process JSON results, and provide feedback. These operations are within the primary scope of the skill's purpose.

firecrawl-search