The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the zsxq-cli binary to interact with the ZSXQ service. This involves executing subcommands like group +list, group +topics, and group +hashtags to retrieve information. These operations are within the scope of the skill's documented purpose for group management.- [PROMPT_INJECTION]: A surface for indirect prompt injection exists because the skill retrieves and processes untrusted content (topics, comments, and hashtags) from the ZSXQ platform. * Ingestion points: External data enters the agent context through tools described in references/zsxq-group-topics.md and references/zsxq-group-hashtags.md. * Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the provided files. * Capability inventory: The skill performs read and search operations using zsxq-cli. * Sanitization: No evidence of sanitization or validation of the retrieved external content was found.

zsxq-group