The Agent Skills Directory

[SAFE]: The skill utilizes the verified vendor's official command-line interface tools (firecrawl and firecrawl-cli) to perform site mapping and discovery tasks.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external websites, which serves as a potential surface for indirect prompt injection.
Ingestion points: The firecrawl map command in SKILL.md takes external URLs as input to discover site structures.
Boundary markers: No explicit delimiters or boundary markers are defined in the instructions to isolate external data from the agent's context.
Capability inventory: The skill is authorized to execute firecrawl and npx firecrawl-cli commands as specified in the allowed-tools metadata of SKILL.md.
Sanitization: The skill does not provide instructions for sanitizing or validating the URL lists retrieved from external sources before further processing.
[NO_CODE]: The skill does not bundle any custom scripts or executable files, relying entirely on the host environment's pre-installed or standard vendor tools.

firecrawl-map