initiative-architecture
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
gh(GitHub) CLI to create and manage issues, labels, and milestones. These are standard project management operations within the GitHub ecosystem. - [DYNAMIC_EXECUTION]: The skill utilizes an
mcp__memory__create_entitiescall to store initiative metadata in a knowledge graph. This is a common pattern for AI agents to maintain state and context across sessions. - [DATA_EXPOSURE]: While the skill handles project information and original user requests, it focuses on public or project-specific documentation within issues and does not access sensitive local files or environment variables like
.envor SSH keys. - [PROMPT_INJECTION]: No evidence of instructions designed to bypass safety filters, override system prompts, or exfiltrate internal agent configurations was found.
Audit Metadata