obsidian-markdown-structure
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious behaviors, network requests, or sensitive file access were found in the instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface as it ingests untrusted data via the Read tool and has write capabilities via the Edit tool. However, the risk is minimal because the skill's logic is constrained to structural validation of markdown formatting rather than content interpretation. Evidence Chain: 1. Ingestion points: Read tool (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Edit tool (SKILL.md). 4. Sanitization: Absent.
Audit Metadata