bolder
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill body consists of aesthetic guidelines and constraints for UI development. No commands, network operations, or obfuscated payloads are present.
- [INDIRECT_PROMPT_INJECTION]: The skill references a file path via $ARGUMENTS to perform code modifications. This defines a surface for untrusted data ingestion.
- Ingestion points: The target file path provided in $ARGUMENTS within SKILL.md.
- Boundary markers: Absent.
- Capability inventory: The skill specifies the capability to edit code.
- Sanitization: Absent.
Audit Metadata