dd-product-recommender
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's functionality is restricted to providing textual recommendations and justifications based on project metadata. It does not perform any destructive actions or unauthorized data modifications.
- [SAFE]: The skill includes explicit behavioral guardrails that forbid the agent from generating installation instructions, calling onboarding tools, or editing any codebase files.
- [SAFE]: Detection logic relies on identifying standard project manifests (e.g., package.json, go.mod, requirements.txt) and directory structures, which is a benign operation for technology identification.
- [SAFE]: No patterns of prompt injection, obfuscation, or persistence were detected within the instructions or the provided reference data.
- [SAFE]: The skill does not perform network operations or call external APIs; it uses a platform-provided tool (AskUserQuestion) for interactive project selection only when multiple roots are detected.
Audit Metadata