jev-control-plane

Warn

Audited by Snyk on Nov 17, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (low risk: 0.10). The required runtime path is route-skills, which can reach a public registry through publicRegistryFallback when the gate fails, and prune-context, which reads arbitrary caller-supplied blocks; the agent must trigger these, so outsider text is low risk rather than delivered unprompted.

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

  • Attempt to modify system services in skill instructions detected (medium risk: 0.40). The skill directs the agent to apply configuration that writes user-level files (~/.agents/jev/agents.json), install hooks into host agent configs via hooks-install --apply, and start background local model servers, but it never requests sudo, system file edits, or account creation, and it asks for approval before downloads or data transmission.

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 17, 2026, 03:49 AM
Issues
2