code-review-dotnet

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process and analyze external, untrusted C# and .NET source code files, which poses a risk of indirect prompt injection if those files contain malicious instructions.
  • Ingestion points: The skill ingests .cs source files, .csproj project files, and .sln solution files during the code review process (specified in SKILL.md).
  • Boundary markers: There are no explicit instructions or delimiters defined to isolate the untrusted source code or to instruct the agent to ignore embedded instructions within that data.
  • Capability inventory: The skill utilizes tools including semgrep, security-code-scan, codeql, and ripgrep to analyze the provided files (specified in SKILL.md frontmatter).
  • Sanitization: The skill does not provide mechanisms for sanitizing, escaping, or validating the external content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 11:01 PM
Security Audit — agent-trust-hub — code-review-dotnet