obsidian
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads and refactors local Markdown files, which serves as a potential ingestion point for untrusted data (e.g., clipped web content). • Ingestion points: Reads .md files from the vault as described in SKILL.md. • Boundary markers: No specific markers or 'ignore embedded instructions' prompts are present. • Capability inventory: The agent can modify vault files and execute local URI schemes. • Sanitization: No sanitization or filtering of external content is mentioned.
- [DYNAMIC_EXECUTION]: The skill generates and recommends JavaScript-based 'Templater' scripts to automate file properties and organizational workflows within the local vault environment.
Audit Metadata