skills/thaitype/chief/shape-up/Gen Agent Trust Hub

shape-up

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No security issues were detected. The skill consists entirely of natural language instructions for a collaborative design workflow.
  • [DATA_EXPOSURE]: The skill intentionally writes user-provided design details to a local markdown file (e.g., design-spec.md). This is its primary stated purpose and is performed under user direction.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to generate a design specification.
  • Ingestion points: User descriptions of project vision, scope, and components.
  • Boundary markers: None explicitly defined in the prompt instructions.
  • Capability inventory: File-write capability is used to save the resulting specification.
  • Sanitization: None. However, since the output is intended to be a markdown document and not executable code, the risk is minimal.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 12:35 AM
Security Audit — agent-trust-hub — shape-up