agent-native-reviewer
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed exclusively of markdown documentation and instructional content for an AI agent. It does not contain any executable scripts, binary files, or configuration-driven command execution.
- [PROMPT_INJECTION]: The skill defines a specific role and review process for the agent. It does not contain instructions designed to bypass safety filters, ignore prior rules, or extract system prompts. While the skill is designed to ingest and analyze untrusted code (representing an indirect prompt injection surface), this is inherent to its primary purpose as a code reviewer and is handled within the context of instructional analysis.
- [EXTERNAL_DOWNLOADS]: No remote resources, external scripts, or package manager commands (such as npm or pip) are referenced or used within the skill.
- [DATA_EXFILTRATION]: There are no hardcoded credentials, sensitive file path accesses, or network-enabled operations (like curl or fetch) that could lead to data exfiltration.
Audit Metadata