The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes Bash tools to execute crw commands and curl for web scraping and API interaction.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes untrusted data from external URLs.
Ingestion points: Data enters the agent's context through external web content fetched by crw scrape and curl commands in SKILL.md.
Boundary markers: The instructions do not define explicit delimiters or warnings to ignore instructions embedded in the scraped content.
Capability inventory: The skill has access to tool execution via Bash(crw:*) and Bash(curl:*) as well as file reading via Read.
Sanitization: There are no documented sanitization or filtering steps for the ingested external data.

crw-scrape