reviewing-technical-design
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely instructional and does not perform any sensitive operations such as network requests, file system modifications, or command execution. It does not specify any 'allowed-tools' in the frontmatter, limiting its scope to text processing.
- [SAFE]: No external dependencies, package installations (npm/pip), or remote code execution patterns were found in the skill or its associated reference files.
- [SAFE]: There is no evidence of obfuscation, hidden content, or prompt injection attempts. The instructions are transparent and focused on the stated purpose of document review.
- [SAFE]: The skill handles untrusted data (the design documents to be reviewed), which is an ingestion point for indirect prompt injection. However, because the skill has no dangerous capabilities or tool access, the risk is negligible. The workflow is restricted to emitting a text-based verdict and findings.
Audit Metadata