meta-reviewing-web-reviewing
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill provides instructions for code review patterns. It does not execute commands, access the network, or modify the filesystem.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze code diffs, creating an indirect prompt injection surface. (1) Ingestion points: React component and hook diffs provided to the agent for review. (2) Boundary markers: None explicitly defined; relies on platform context. (3) Capability inventory: No dangerous tools (file system, network, or code execution) are used by the skill. (4) Sanitization: None specified. Given that this is the primary purpose of the skill and no dangerous capabilities are present, this does not represent a significant risk.
- [EXTERNAL_DOWNLOADS]: The metadata.yaml file references a schema from the agents-inc GitHub repository for configuration validation. This is a legitimate reference to a resource from the skill author.
Audit Metadata