micro-optimizer
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external code provided via the 'code' input parameter, which creates a surface for indirect prompt injection.
- Ingestion points: The 'code' property in the input schema defined in SKILL.md.
- Boundary markers: Absent; there are no instructions on how to handle or delimit potentially malicious instructions embedded within the provided source code.
- Capability inventory: The skill utilizes file system tools (Write, Edit, Read, Grep, Glob), meaning a successful injection could lead to unauthorized file modifications.
- Sanitization: Absent; no validation, escaping, or filtering of the input code is specified.
Audit Metadata