The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the zsxq-cli binary to perform queries against the Knowledge Planet API, mapping shortcuts like +info and +footprints to specific CLI commands.
[DATA_EXPOSURE]: Accesses personal information including user IDs, account statuses, and geographic location from the platform. This data is intended for display to the user and no unauthorized exfiltration patterns were detected.
[PROMPT_INJECTION]: The skill processes user-generated content (post summaries and titles) retrieved via the +footprints command, which presents a surface for indirect prompt injection.
Ingestion points: Output from zsxq-cli user +footprints containing topic digests and titles from the ZSXQ platform.
Boundary markers: Absent; the agent is instructed to read the CLI output directly without specific delimiters or warnings about embedded instructions.
Capability inventory: The agent has the capability to execute shell commands via zsxq-cli and access various platform APIs.
Sanitization: Absent; no validation or escaping of the retrieved content is performed before the agent processes it.

zsxq-user