game-ui-extension

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates entirely on local project documentation (e.g., gdd.md, prd.md, research.md) to generate UI design specifications. No patterns associated with malicious activity, such as remote code execution, data exfiltration, or credential theft, were detected.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from project files like research.md and user-provided descriptions. While there are no explicit boundary markers to delimit this external content, the risk is negligible because the skill lacks dangerous capabilities such as network access or shell command execution. The output is restricted to writing YAML and Markdown files within the project workspace.
  • Ingestion points: gdd.md, prd.md, interaction.md, spec.md, research.md, contracts/style-contract.yaml, plan.md, contracts/screen-contract.yaml
  • Boundary markers: Absent
  • Capability inventory: File writes to screen-contract.yaml, plan.md, and tasks.md. No network or subprocess capabilities.
  • Sanitization: Absent
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 03:10 PM
Security Audit — agent-trust-hub — game-ui-extension