game-production-feature

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it is designed to ingest untrusted feature requirements and local files to generate code.
  • Ingestion points: User-provided feature scope requests and local files such as ../../shared/checklists/production-feature-checklist.md (SKILL.md).
  • Boundary markers: None identified in the skill instructions.
  • Capability inventory: Compatibility notes in SKILL.md indicate the skill works best with file read/write and shell/build/test access.
  • Sanitization: No explicit sanitization or validation of the input feature requirements is present.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 12:35 PM
Security Audit — agent-trust-hub — game-production-feature