zooming-out-on-code
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security threats or malicious patterns were detected. The skill provides instructions for code summarization and architectural analysis using local files and standard search tools. While the skill represents a surface for indirect prompt injection (Category 8) as it processes codebase content, it is limited to informational summaries with no dangerous side effects. 1. Ingestion points: Reads local files such as CONTEXT.md and source code. 2. Boundary markers: Absent. 3. Capability inventory: Uses read-only tools like grep and LSP. 4. Sanitization: Absent. The skill does not perform network operations, credential harvesting, or unauthorized command execution.
Audit Metadata