combat-design
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): No patterns of instruction override, jailbreaking, or safety filter bypass were detected. The persona-based instructions are consistent with the skill's stated purpose.
- [Data Exposure & Exfiltration] (SAFE): No sensitive file paths, hardcoded credentials, or network exfiltration patterns are present.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not include or download any external scripts or packages.
- [Obfuscation] (SAFE): No encoded strings, homoglyphs, or hidden Unicode characters were found.
- [Indirect Prompt Injection] (SAFE): While the skill references local files (references/*.md), it lacks the capabilities (such as command execution or network access) that would create an exploitable attack surface.
Audit Metadata