dotnet-logging-exceptions
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to review .NET code changes provided by a user. This introduces a surface where malicious instructions could be embedded within the code being reviewed (e.g., in comments or string literals) to influence the agent's behavior. However, the skill provides specific safety guidelines to mitigate accidental disclosure or misconfiguration.
- Ingestion points: The skill processes external code changes provided during an agent session (SKILL.md).
- Boundary markers: None explicitly defined in the instructions to separate code from instructions, though the guidelines focus on technical review.
- Capability inventory: The skill is restricted to providing review feedback and does not involve file system writes, network operations, or command execution.
- Sanitization: No specific sanitization of the input code is defined, relying on the underlying model's guardrails.
Audit Metadata