photoshop-adjustment

Pass

Audited by Gen Agent Trust Hub on Jul 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's functionality is consistent with its stated purpose of providing Adobe Photoshop automation tools. No evidence of prompt injection, data exfiltration, or persistence mechanisms was found.
  • [COMMAND_EXECUTION]: The batch_play tool allows the agent to execute raw ActionDescriptor descriptors. This is a powerful, low-level Photoshop interface used for advanced automation. The analysis confirms this tool interfaces with the Photoshop application via the adobe.photoshop library and does not execute arbitrary shell commands on the host operating system.
  • [PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection via the name and descriptors arguments in the add_channel and batch_play tools. However, these inputs are used solely for Photoshop-specific operations, and the skill includes no instructions that attempt to override the AI agent's safety guidelines or core behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 26, 2026, 08:40 AM