codeguard-csharp
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source code and project configuration files which could potentially contain malicious instructions intended to subvert the agent's logic during analysis or formatting tasks.
- Ingestion points: The skill reads and analyzes
*.cssource files,*.slnsolution files, and*.csprojproject files (SKILL.md). - Boundary markers: No specific delimiters or markers are defined to isolate untrusted file content from the agent's core instructions.
- Capability inventory: The skill utilizes the
dotnetCLI for formatting and verification, and instructs the agent to execute project-specific tests and build gates (SKILL.md, Step 7 of Workflow). - Sanitization: The skill lacks explicit sanitization or validation logic for the content of ingested files before they are processed by the toolchain or the agent.
Audit Metadata