create-plan

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, hardcoded secrets, or dangerous command execution were detected in the skill definition or the accompanying license file.
  • [PROMPT_INJECTION]: The skill processes untrusted data by scanning project files such as README.md, which represents an indirect prompt injection surface. 1. Ingestion points: Local project files mentioned in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: The skill is restricted to read-only operations and lacks file-writing or network access. 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 03:19 PM
Security Audit — agent-trust-hub — create-plan