agent-native-reviewer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Indirect Prompt Injection (SAFE): The skill is designed to ingest and analyze untrusted data in the form of source code and pull request descriptions. While this is an ingestion surface for indirect prompt injection, the skill itself lacks any tools or execution capabilities that could be exploited.
- Ingestion points: Source code, PR descriptions, and application designs provided for review.
- Boundary markers: None defined in the prompt instructions.
- Capability inventory: The skill is a pure instruction set with no associated executable tools or scripts.
- Sanitization: None.
- SAFE (SAFE): No malicious patterns, command execution, or obfuscation were detected. The skill uses standard markdown and XML-style tags for prompt engineering.
Audit Metadata