data

Warn

Audited by Snyk on Nov 18, 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). Commenters who join a shared dashboard over the LAN can post comments that the agent reads through open-artifact comments and the comment-handling workflow, without the agent selecting a specific item first.

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

  • Attempt to modify system services in skill instructions detected (low risk: 0.30). The skill is a dashboard-building guide that works in its own project folder and never asks for sudo, system file edits, user account creation, or service/SSH config changes; the main machine-level concern is that it tells the agent to request approval to run a local server past a sandbox's network restriction.

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 18, 2026, 12:29 PM
Issues
2