The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill utilizes npx firecrawl which downloads the Firecrawl CLI package from the public npm registry. This is a standard installation method for the vendor's official tooling.
[COMMAND_EXECUTION]: The skill executes shell commands via firecrawl and npx firecrawl to perform crawling operations. This includes writing extracted data to the local filesystem using the -o or --output flags.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its core functionality.
Ingestion points: Untrusted data is ingested from external websites during the crawl process as described in SKILL.md.
Boundary markers: The skill does not provide instructions for the agent to use delimiters or ignore instructions embedded within the crawled content.
Capability inventory: The skill has the capability to perform network requests (crawling) and write files to the local system via Bash commands.
Sanitization: There is no evidence of sanitization or validation performed on the ingested web content before it is returned to the agent's context.

firecrawl-crawl