inbox
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary functionality is limited to managing files within the
~/Obsidian/directory. It uses specific local paths and references internal configuration files (CONTEXT.md,CONVENTIONS.md) to guide behavior. - [PROMPT_INJECTION]: The skill processes content from the
~/Obsidian/Inbox/directory, which constitutes an indirect prompt injection surface as these files may contain malicious instructions designed to influence the triage process. - Ingestion points:
~/Obsidian/Inbox/(SKILL.md) - Boundary markers: Absent; the skill does not use specific delimiters or warnings to ignore instructions within the ingested files.
- Capability inventory: The skill can list, move, create, update, and delete files within the
~/Obsidian/vault (SKILL.md). - Sanitization: No sanitization or validation of the inbox content is performed before processing.
Audit Metadata