dotnet-advisor
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project metadata files which constitutes an indirect prompt injection surface.
- Ingestion points: In Step 1, the skill reads Target Framework Monikers (TFMs) and project signals from
.csproj,Directory.Build.props, andglobal.jsonfiles to determine the project version. - Boundary markers: The instructions do not specify the use of delimiters, XML-escaping, or "ignore embedded instructions" warnings when the agent reads the content of these project files.
- Capability inventory: The data extracted from these files is used to influence the selection and behavior of other specialist skills within the suite, which may possess more extensive file-system or command-execution capabilities.
- Sanitization: There is no instruction to validate or sanitize the strings extracted from the configuration files before using them to adapt the agent's guidance or planning logic.
Audit Metadata