vault-review

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted content from user notes to generate daily plans and summaries, establishing a surface for indirect prompt injection.
  • Ingestion points: Reads from yesterday's daily notes, active project files, and recently modified notes to gather context (SKILL.md).
  • Boundary markers: The instructions do not define delimiters or specific 'ignore' instructions for the data ingested from the vault.
  • Capability inventory: The skill possesses file-writing capabilities to create and append content to daily notes (SKILL.md).
  • Sanitization: No sanitization or validation of the ingested note content is performed before it is passed to high-capability models for synthesis.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 03:46 PM
Security Audit — agent-trust-hub — vault-review