plan
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill defines a logical workflow for planning tasks and does not contain any malicious patterns such as obfuscation, persistence mechanisms, or privilege escalation.
- [NO_CODE]: The skill consists purely of instructional markdown for the AI agent and does not include or download any executable scripts or binary files.
- [PROMPT_INJECTION]: The skill interacts with user-provided task descriptions and reads plan files from the
.omc/plans/directory. While this creates a surface for Indirect Prompt Injection, the skill lacks access to any tools (e.g., shell, network, or file writing) that could be exploited to cause harm, rendering the surface safe.
Audit Metadata