pm-execute-change-control
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains no executable code, remote dependencies, or hidden instructions. It is designed solely to guide the agent through a logical project management workflow.
- [DATA_EXFILTRATION]: While the skill instructions suggest reading a project context file (
.agents/project-context.md), this is restricted to the local environment and intended for project-related reasoning. No network operations or commands to transmit data externally were detected. - [COMMAND_EXECUTION]: The skill does not perform any system-level command execution or shell interactions. It relies on the agent's existing capabilities to process text and project data.
- [PROMPT_INJECTION]: The instructions focus on structured output and logical steps for change control. There are no attempts to bypass safety filters or override agent behavior maliciously.
Audit Metadata