write-feature
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely instructional, providing a guide for software development processes. It does not contain any executable scripts, binary files, or remote dependencies.
- [SAFE]: No network operations, data exfiltration patterns, or attempts to access sensitive system credentials (e.g., .ssh, .aws) were detected.
- [SAFE]: The instructions do not contain prompt injection techniques or attempts to bypass AI safety filters. It encourages the agent to halt and ask questions when faced with ambiguity rather than guessing.
- [SAFE]: The skill references local project files (specs, tasks, and AGENTS.md) which is standard behavior for a development-focused AI agent.
Audit Metadata