mstest
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill relies on external project files to define its execution parameters, creating a potential vector for instruction injection.
- Ingestion points: The agent is instructed to read AGENTS.md for project constraints and test commands, and .csproj files for project configuration.
- Boundary markers: The instructions lack specific delimiters or boundary markers to isolate data ingested from repository files.
- Capability inventory: The skill uses capabilities for searching the filesystem (ripgrep), modifying files, adding packages, and executing shell commands (dotnet test).
- Sanitization: No sanitization or validation of content retrieved from the repository is required before use in command execution.
Audit Metadata