code-review
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, untrusted data in the form of code diffs and pull requests. While this presents an attack surface where an attacker could embed malicious instructions in a code change, the skill itself lacks any dangerous capabilities (such as file writing, shell execution, or network access) to exploit such an injection.
- Ingestion points: Processes pull request content and code diffs provided by the user.
- Boundary markers: The instructions do not define specific delimiters for separating the untrusted code from the instructions.
- Capability inventory: The skill body and metadata do not request or use any tools for system modification or network communication.
- Sanitization: No explicit sanitization or instruction to ignore embedded commands is present.
- [SAFE]: No patterns of obfuscation, remote code execution, credential theft, or persistence were detected. The skill functions solely as a logical framework for the agent to use during analysis.
Audit Metadata