zj-obsidian-vault
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill interacts with external Markdown files within an Obsidian vault, which serves as an ingestion point for untrusted data.
- Ingestion points: The agent reads note content from
/mnt/d/Obsidian Vault/AI Research/usinggrepandfindcommands as described inSKILL.md. - Boundary markers: There are no specific delimiters or instructions defined to distinguish between data content and agent instructions.
- Capability inventory: The workflows focus on search (
grep,find) and manual note creation. No automated script execution or network operations are present. - Sanitization: The skill does not implement sanitization or filtering for the content retrieved from the Markdown files.
Audit Metadata