psd-instructional-vision
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- PROMPT_INJECTION (SAFE): While the document contains a section titled 'System Prompt Injection,' the instructions are designed to set a benign educational persona for the AI and do not attempt to bypass safety filters or override fundamental system instructions.
- DATA_EXFILTRATION (SAFE): No access to sensitive file paths, hardcoded credentials, or network exfiltration patterns were identified. The skill only utilizes the 'Read' tool for local documentation.
- REMOTE_CODE_EXECUTION (SAFE): The skill does not perform external downloads, package installations, or dynamic script execution.
Audit Metadata