agent-native-reviewer
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious code, obfuscation, or data exfiltration patterns were detected. The skill consists entirely of high-level instructions for reviewing agent-related workflows.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to analyze external repository data (code, PRs, docs), which presents a potential surface for indirect prompt injection.
- Ingestion points: Analyzes
SKILL.mdfiles,.agents/directories, PR feedback, and CLI command outputs within a repository. - Boundary markers: None explicitly defined in the instructions to separate untrusted data from the agent's core logic.
- Capability inventory: Instructs the agent to use
Browser,Chrome,Computer Use, and file-editing tools to verify parity. - Sanitization: No sanitization of the input text or file content is described.
Audit Metadata