code-simplifier
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by processing external data.
- Ingestion points: The agent is instructed to analyze and refine "recently modified code" (SKILL.md).
- Boundary markers: There are no instructions to use delimiters or explicit "ignore embedded instructions" warnings for the code being simplified.
- Capability inventory: The skill contains no scripts, but the agent is tasked with modifying files and applying refinements autonomously.
- Sanitization: No sanitization or input validation is specified for the code being processed.
- [PROMPT_INJECTION]: The skill instructs the agent to "operate autonomously and proactively... without requiring explicit requests." This autonomy reduces user oversight, which can be a risk if the agent inadvertently follows malicious instructions hidden in the code it is simplifying.
Audit Metadata