code-review
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data, specifically code diffs, tickets, and repository standards. This creates a surface for indirect prompt injection if the external data contains instructions intended to manipulate the agent's behavior.
- Ingestion points: Git diffs, specification documents, and ticket descriptions processed as inputs (SKILL.md).
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the prompt instructions.
- Capability inventory: The skill is purely instructional and does not define any tool use, network calls, or file system modifications within its own logic.
- Sanitization: No input sanitization or validation mechanisms are defined.
- [SAFE]: The skill references external source documentation from well-known technology community contributors on GitHub. These references are for attribution and guidance and do not involve remote code execution or automated downloads.
Audit Metadata