visual-verdict
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely instructional and serves as a template for visual QA tasks. It does not include any scripts, commands, or network-enabled operations.
- [INDIRECT_PROMPT_INJECTION]: The skill incorporates external content via the
{{ARGUMENTS}}placeholder. While this is a theoretical surface for indirect prompt injection, the risk is mitigated by the skill's strict requirement for a specific JSON-only output and the absence of any tools or capabilities that could be leveraged for malicious actions.
Audit Metadata