handbook-updates
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill's behavior matches its stated purpose of managing handbook updates. It uses a structured workflow for diffing policies and flagging inconsistencies without executing external code or scripts.
- [PROMPT_INJECTION]: The skill ingests untrusted data from user-provided policy changes and handbook documents, which constitutes a surface for indirect prompt injection. However, this is inherent to its primary document-processing function and lacks dangerous execution capabilities.
- Ingestion points: Processes user inputs for policy text and reads existing handbook files from the local filesystem.
- Boundary markers: No specific delimiters or safety instructions are defined to separate ingested text from the agent's internal logic.
- Capability inventory: Reading local configuration and handbook files, and writing markdown output to matter-specific subdirectories within the plugin configuration path.
- Sanitization: No explicit sanitization or validation of external policy content is implemented.
Audit Metadata