update-cursor-settings

Warn

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: MEDIUMPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted user instructions to modify local application configurations.
  • Ingestion points: User-provided natural language instructions for settings changes.
  • Boundary markers: None are specified to separate user input from system instructions.
  • Capability inventory: The skill utilizes file system read and write capabilities to modify the settings.json file.
  • Sanitization: No sanitization is performed beyond basic JSON syntax validation.
  • [DATA_EXFILTRATION]: The skill accesses sensitive application configuration files (settings.json) that contain user preferences and environment details. While intended for editor configuration, this access represents a potential exposure of sensitive application data.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 18, 2026, 02:41 AM
Security Audit — agent-trust-hub — update-cursor-settings