subagent-driven-development

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill describes an orchestration workflow for managing software implementation. No evidence of prompt injection, data exfiltration, or malicious command execution was found within the instructions.\n- [PROMPT_INJECTION]: The skill explicitly requires that subagents 'should never inherit your session's context or history', providing a defense against context contamination and unauthorized data access between tasks.\n- [SAFE]: The use of external resources like prompt templates and other skills from the 'superpowers' suite is consistent with the vendor's own ecosystem and intended functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 11:56 PM
Security Audit — agent-trust-hub — subagent-driven-development