rnd-code-simplify
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill operates on code modified within the session, creating a surface for indirect prompt injection. Malicious instructions embedded in comments or strings within the code could influence the agent's refactoring logic.
- Ingestion points: Code recently modified or written in the current session (SKILL.md).
- Boundary markers: No delimiters or instructions to ignore embedded commands are specified for the input code.
- Capability inventory: The skill is authorized to autonomously modify and rewrite project source code.
- Sanitization: No validation or sanitization of the code content is performed to prevent the execution of embedded prompts.
Audit Metadata