gsd-set-profile

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill accepts a profile argument used in workflows that perform file operations and command execution, creating a surface for indirect prompt injection. Ingestion points: argument in SKILL.md. Boundary markers: None defined. Capability inventory: Read, Write, and Bash tools. Sanitization: Logic includes validation against specific profile values (quality/balanced/budget).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 07:07 PM