skills/canhassancode/skills/inbox/Gen Agent Trust Hub

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
Risk Level
SAFE
Analyzed
Jul 8, 2026, 01:31 PM
Security Audit — agent-trust-hub — inbox