design-lifecycle

Pass

Audited by Gen Agent Trust Hub on Jul 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a multi-layered agent orchestration (Architect, Copy, Measurement, and Critic) to design retention flows. The Critic agent enforces a strict 6-dimension rubric and four hard gates to ensure quality and safety.
  • [SAFE]: The skill explicitly prohibits exfiltration of Personally Identifiable Information (PII) and the autonomous sending of emails, restricting its scope to design only.
  • [SAFE]: The included utility script scripts/bootstrap-experience.ts is used for initializing a local context storage directory. It follows security best practices by using atomic file creation (flag: 'wx') and explicit symlink checks to prevent file system attacks.
  • [SAFE]: Agent instructions are focused on marketing methodology and do not contain prompt injection markers, role-play bypasses, or instructions to ignore safety guidelines.
  • [SAFE]: The tool permissions (Bash, WebFetch, Read, Grep, Glob) are aligned with the skill's stated purpose for research and internal project context management.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 4, 2026, 10:16 PM
Security Audit — agent-trust-hub — design-lifecycle