code-simplifier
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to executegit difffor identifying changes andnpm testto verify code integrity. These operations are essential to its primary function of code simplification and testing. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) due to how it processes untrusted data.
- Ingestion points: The agent reads source code from the local filesystem using
Read,Glob,Grep, and the output ofgit diff. - Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions embedded within the code being analyzed (e.g., in comments or strings).
- Capability inventory: The agent has the ability to modify files via
EditandWrite, and execute arbitrary commands via theBashtool. - Sanitization: There is no evidence of content sanitization or validation to prevent the model from following instructions found within the code files it processes.
Audit Metadata