modern-patterns-audit
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious behavior, obfuscation, or security threats were identified in the skill instructions.
- [NO_CODE]: The skill consists solely of Markdown text and prompt instructions, with no associated scripts or binaries.
- [PROMPT_INJECTION]: The skill processes user-provided Unity scripts, creating a surface for indirect prompt injection. * Ingestion points: User scripts provided during agent interaction. * Boundary markers: Absent. * Capability inventory: None. * Sanitization: Absent.
Audit Metadata