The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute the babeliocli command-line tool to perform book searches and fetch metadata or reviews. It additionally utilizes standard system utilities including jq, head, and sort for filtering and formatting the output data.
[PROMPT_INJECTION]: The skill processes user-generated content from the Babelio website (book reviews), creating a surface for indirect prompt injection. If a review contains malicious instructions, the agent may inadvertently follow them when processing the text.
Ingestion points: External review text fetched via babeliocli reviews in SKILL.md.
Boundary markers: None; the review content is piped directly into processing tools without delimiters or safety warnings.
Capability inventory: Execution of shell commands (babeliocli, jq, head, sort) as described in SKILL.md.
Sanitization: No sanitization or validation of the retrieved review body is specified.

babeliocli-discover