llm-wiki-documentation
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of documentation and guidance for creating AI-ready wiki pages. It contains no executable scripts, shell commands, or network operations.
- [DATA_EXFILTRATION]: The provided guidance includes explicit instructions in the "Source Boundaries" section to exclude sensitive information such as secrets, private prompts, tokens, credentials, or customer data from documentation.
- [INDIRECT_PROMPT_INJECTION]: The skill mitigates the risk of indirect prompt injection by defining a strict "Context Layers" hierarchy. This hierarchy ensures that system instructions and workflow gates always maintain higher authority than wiki content, preventing external documentation from overriding core agent logic.
Audit Metadata