codely-plan-create
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a structured planning workflow that requires explicit user approval before creating files or initiating implementation phases.
- [SAFE]: File system modifications are limited to the
.agents/plans/directory, which is a standard location for agent-generated planning artifacts. - [SAFE]: Codebase exploration is performed through delegated subagents with specific, narrow scopes, which reduces the risk of the primary agent processing excessive untrusted data directly.
- [SAFE]: The skill leverages other local skills (e.g., git commit and implementation tools) based on user selection, maintaining human-in-the-loop control for sensitive operations.
- [SAFE]: External references to the author's website (codely.com) and the use of vendor-prefixed skills are consistent with the skill's stated purpose and identity.
- [SAFE]: While the skill ingests project documentation and subagent reports (representing an indirect prompt injection surface), it manages this risk through reasoning synthesis and a multi-step approval process.
Audit Metadata