wiki-lint
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements strong security boundaries during the 'Config Discovery' phase, specifically prohibiting searches at the OS or user-home root levels to prevent directory traversal and exposure of sensitive system files.\n- [SAFE]: References to the author's public GitHub repository are included for documentation purposes and align with the stated purpose of the skill ecosystem.\n- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes user-controlled markdown files to identify conceptual issues and missing connections. This is a functional requirement for wiki auditing.\n
- Ingestion points: index.md, Overview.md, and all markdown files identified in the vault (SKILL.md Step 1).\n
- Boundary markers: Absent; files are processed without explicit delimiters or 'ignore' instructions for embedded content.\n
- Capability inventory: Filesystem read access; write access limited to the archive/ directory and log.md. No network access or subprocess execution tools are required.\n
- Sanitization: Absent; the skill does not specify sanitization or validation of page content prior to interpretation by the agent.
Audit Metadata