zmm-flow
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text (scripts) to perform logic and flow checks.
- Ingestion points: User scripts provided via commands like
/zmm-floware processed during the analysis workflow. - Boundary markers: The instructions do not define specific delimiters or guardrails to separate user content from agent instructions.
- Capability inventory: The skill is restricted to reading local reference files in
zmm/references/and managing local memory in{vault}/08-技能记忆/. It lacks network access or the ability to execute shell commands. - Sanitization: There is no explicit sanitization or filtering mentioned for the user-provided text before analysis.
- [SAFE]: The skill does not perform network operations, remote code execution, or privilege escalation. All file access is scoped to the agent's internal reference and memory directories.
Audit Metadata