subagent-driven-development

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • SAFE (SAFE): The skill is purely instructional and consists of process guidelines. It does not include any executable scripts, shell commands, or network-reaching operations.
  • Indirect Prompt Injection (LOW): This skill defines an attack surface for indirect prompt injection as it processes external implementation plans. 1. Ingestion points: 'Read plan, extract all tasks' in SKILL.md. 2. Boundary markers: Not explicitly defined in instructions. 3. Capability inventory: Mentions implementing, testing, and committing code. 4. Sanitization: No specific sanitization or filtering logic is described for the input tasks. This risk is categorized as LOW as it is inherent to the intended primary skill purpose of task execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:58 PM