llm-wiki
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data (articles, papers, and reports) which represents a surface for indirect prompt injection.
- Ingestion points: Raw source documents are read from the
~/.workbuddy/wiki-knowledge/raw/directory as specified in SKILL.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when the AI reads and summarizes these raw sources.
- Capability inventory: The skill has access to
Read,Write,Bash,Grep, andGlobtools (SKILL.md). - Sanitization: There is no mention of content sanitization or validation before the AI incorporates data from the sources into the persistent wiki pages.
Audit Metadata