code-simplifier
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes untrusted data (files modified in the session). However, its instructions are focused on structural code analysis rather than instruction following from the data.
- Ingestion points: Reads all files modified in the session (SKILL.md).
- Capability inventory: The agent performs file read and rewrite operations to simplify code.
- Boundary markers: Absent; the instructions do not include specific delimiters or warnings to ignore instructions embedded within the reviewed code.
- Sanitization: Absent; there is no evidence of content validation or filtering before processing the code.
Audit Metadata