llm-wiki
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The ingestion workflow processes user-provided files from a local directory to build the wiki. This creates a surface for indirect prompt injection, though it is mitigated by instructions to share takeaways and confirm details with the user before updating pages.
- [COMMAND_EXECUTION]: Includes example read-only shell commands for inspecting the wiki log. These commands (grep, tail) are used for status reporting and do not pose a risk.
- [EXTERNAL_DOWNLOADS]: Suggests an optional installation of an external search utility (@tobilu/qmd) for large wikis, which is a common practice for enhancing functionality and is left to the user's discretion.
Audit Metadata