skills/unnoo/zsxq-skill/zsxq-topic/Gen Agent Trust Hub

zsxq-topic

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the zsxq-cli binary to interact with the Knowledge Planet API for topic management. This includes operations for searching, viewing, creating, replying to, and deleting topics.
  • [PROMPT_INJECTION]: The skill identifies a potential indirect prompt injection surface where user-provided content (titles, text, queries) is passed to CLI commands. It mitigates this risk by explicitly instructing the agent to confirm the content and target星球/主题 with the user before performing any write or delete operations.
  • [SAFE]: All external resources and command patterns are consistent with the skill's stated purpose of managing Knowledge Planet topics via a vendor-specific CLI tool (zsxq-cli).
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 03:01 AM