fable-planning
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a 'Hard Rules' section that restricts the agent to read-only codebase access and explicitly forbids code edits, builds, installations, tests, or any state-changing commands.
- [SAFE]: Evidence-based reasoning is mandatory; the agent must provide file paths and line numbers (path:line) for every claim, ensuring all analysis is grounded in the local environment.
- [SAFE]: The framework includes a comprehensive edge-case validation checklist that specifically directs the agent to evaluate security concerns such as untrusted input boundaries and authorization checks in the design phase.
- [SAFE]: No signs of obfuscation, remote code execution, or unauthorized network activity were found. All referenced assets and templates are local to the skill directory.
Audit Metadata