ai-assisted-development

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns detected across the analyzed files. The skill is documentation-centric, focusing on development strategies and orchestration logic.
  • [PROMPT_INJECTION]: The skill describes an inherent surface for indirect prompt injection in its multi-agent orchestration patterns (e.g., in SKILL.md and references/ai-patterns.md), where agents process external data like requirements or curriculum files. However, this is documented as a standard architectural feature, and the skill actively encourages mitigation through its 'Human-in-the-Loop' pattern and automated quality gates.
  • [COMMAND_EXECUTION]: The documentation in references/orchestration-strategies.md suggests using standard development tools (e.g., phpcs, phpstan, phpunit) for quality validation. These are described as user-implemented checks and do not represent unauthorized or hidden command execution by the skill itself.
  • [EXTERNAL_DOWNLOADS]: While the skill mentions an external 'Superpowers' plugin and provides example API URLs for documentation purposes (e.g., https://api.external.com/openapi.json), it does not contain code to perform unauthorized downloads or execute remote scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 12:09 PM