llm-wiki
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a local script,
scripts/lint.mjs, using Node.js to perform structural checks on the wiki folder, such as identifying broken links or missing frontmatter. This execution is restricted to the provided local script and the user-specified wiki directory. - [INDIRECT_PROMPT_INJECTION]: The
ingestoperation reads external source documents which could contain embedded instructions. The skill mitigates this risk by requiring the agent to present a summary of proposed changes and wait for explicit user confirmation before modifying the filesystem.
Audit Metadata