health

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • PROMPT_INJECTION (LOW): The skill identifies a clear surface for indirect prompt injection by processing external data from a knowledge vault.
  • Ingestion points: Vault files including notes, MOCs, and link health data.
  • Boundary markers: Not defined in the provided metadata; sanitization logic would be expected in the SKILL.md or associated logic.
  • Capability inventory: Reading vault structures and generating actionable reports.
  • Sanitization: No sanitization or validation methods are specified in the JSON manifest.
  • NO_CODE (SAFE): The provided skill.json is a metadata manifest and contains no executable commands, shell scripts, or external dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 07:04 AM