log

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues were detected. The skill functions as a diagnostic tool that only reads and lists files from the local .devils-advocate directory.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from local files (.devils-advocate/session.md and files in .devils-advocate/logs/) which constitutes a potential indirect prompt injection surface. The risk is assessed as safe because the skill has no dangerous capabilities that could be abused; it only performs read and glob operations and does not execute code, write files, or access the network. 1. Ingestion points: .devils-advocate/session.md and .devils-advocate/logs/*.md. 2. Boundary markers: Absent. 3. Capability inventory: read and glob tools. 4. Sanitization: None.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 12:52 PM
Security Audit — agent-trust-hub — log