ce-doc-review
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses platform-native tools for file operations and sub-agent management, adhering to the principle of least privilege within the context of its document review functionality.
- [SAFE]: Sub-agent prompts employ structured delimiters (e.g.,
<document-content>) and strictly enforced JSON schemas to mitigate potential indirect prompt injection from reviewed documents. - [SAFE]: The skill implementation includes explicit safeguards (Phase 3.9) to prevent the deletion of sensitive project artifacts in the
docs/directories. - [SAFE]: No obfuscation, hardcoded credentials, or unauthorized network operations were detected in the skill's instructions or referenced files.
Audit Metadata