wiki-update
Pass
Audited by Gen Agent Trust Hub on May 2, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface through its processing of wiki content and user information. 1. Ingestion points: Reads data from 'wiki/index.md', 'wiki/pages/', and 'SCHEMA.md'. 2. Boundary markers: Absent. 3. Capability inventory: Includes file read/write and 'grep' searching. 4. Sanitization: Absent. The skill mitigates this surface by requiring manual confirmation for all writes.
- [COMMAND_EXECUTION]: The skill uses 'grep' to search for internal page references. This is a read-only operation constrained to the wiki directory and used to ensure consistency across the wiki database.
Audit Metadata