dotnet-update-packages
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes external data which creates an indirect prompt injection surface. 1. Ingestion points: NuGet package metadata from
dotnet listand.csprojproject files. 2. Boundary markers: Implicitly handled via structured data formats (JSON/XML). 3. Capability inventory: Modification of project files and execution of project builds. 4. Sanitization: The risk is mitigated by a mandatory human-in-the-loop confirmation step (AskUserQuestion) before any system changes are performed. \n- [SAFE]: No malicious patterns such as obfuscation, credential theft, or unauthorized network operations were detected. The skill's use of commands and file access is strictly limited to the functions required for its stated purpose.
Audit Metadata