code-simplifier
Fail
Audited by Gen Agent Trust Hub on Feb 15, 2026
Risk Level: HIGHPROMPT_INJECTIONNO_CODE
Full Analysis
- PROMPT_INJECTION (HIGH): The skill exhibits a high-risk surface for Indirect Prompt Injection. 1. Ingestion points: Processes 'recently modified code' during the session (SKILL.md). 2. Boundary markers: Absent. The instructions do not define delimiters or provide warnings to ignore instructions found within the processed code. 3. Capability inventory: The skill allows autonomous and proactive file modification ('refining code immediately after it is written'). 4. Sanitization: Absent. No sanitization or validation of the input code is performed.
- NO_CODE (LOW): The skill consists of markdown instructions only and does not contain executable scripts or binary files.
Recommendations
- AI detected serious security threats
Audit Metadata