maa-cli-operate

Warn

Audited by Snyk on Nov 22, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.30). The required workflow runs ocr, reco, and screenshot on the connected device's screen before acting (SKILL.md [35]), and that on-screen text can include outsider-authored content such as game chat, comments, or messages that an outsider can post into a feed the device displays, so under recall-first this is treated as medium even though the agent must navigate to that screen first.

MEDIUM W013: Attempt to modify system services in skill instructions.

  • Attempt to modify system services in skill instructions detected (low risk: 0.10). The skill exposes operational changes, including daemon stop/restart, session close-all, resource download-ocr into the user cache, custom load executing Python, and action shell on the controller, but no supplied text establishes explicit irreversible operational loss, so the gate for medium or high fails.

Issues (2)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W013
MEDIUM

Attempt to modify system services in skill instructions.

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 22, 2026, 01:27 AM
Issues
2