unhappy
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues were identified. The skill instructions are focused on standard frontend development and code refactoring tasks, such as implementing state machines and skeletons.
- [INDIRECT_PROMPT_INJECTION]: The skill demonstrates a surface for indirect prompt injection by processing code provided via
$ARGUMENTSand using the agent's capabilities to edit files directly. However, the risk is considered safe because the skill does not have network access or administrative privileges, and its actions are limited to localized code modifications. - Ingestion points: External code processed through the
$ARGUMENTSparameter. - Boundary markers: No delimiters or 'ignore embedded instructions' warnings are present.
- Capability inventory: The agent is instructed to edit code files directly.
- Sanitization: No validation or sanitization of the input code is defined.
Audit Metadata