scope-control

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional markdown files and contains no logic or code that could be executed maliciously.
  • [NO_CODE]: No scripts, binaries, or package dependencies are included or referenced.
  • [DATA_EXFILTRATION]: No network access or data transfer capabilities are present in the skill definition.
  • [PROMPT_INJECTION]: The skill processes untrusted user game plans, creating an indirect prompt injection surface. 1. Ingestion point: User-provided game plans in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: None across all files. 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 06:39 PM
Security Audit — agent-trust-hub — scope-control