conventions-check
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions are limited to natural language processing of code diffs and local documentation files. No network operations, credential access, or shell command executions are performed.
- [INDIRECT_PROMPT_INJECTION]: The skill processes code diffs which are untrusted external inputs. While this presents an attack surface for indirect prompt injection, it is the primary function of the tool and no dangerous capabilities (like network access or file writes) are exposed to the agent while performing this task.
- Ingestion points: Code diffs provided by the user or agent environment.
- Boundary markers: None specified in the instructions.
- Capability inventory: Reading local files (server/AGENTS.md, clients/AGENTS.md).
- Sanitization: None present.
Audit Metadata