fleet-sync

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 updater installs marketplace plugins, including the design-system plugin from the filipgutica/design-system marketplace, and their skill/plugin content enters agent context without the agent selecting a specific item; this is a marketplace-item exposure, though the publisher appears to be the skill owner.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (medium risk: 0.30). The skill clones the individually owned GitHub repository filipgutica/filip-stack during setup and then executes its updater code, and it installs the design-system plugin from the individually owned filipgutica/design-system marketplace; neither is strong first-party provenance, and no warning signs are present, so the tier is common/reputable unofficial (medium).

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 updates plugins, skills, and user-level config across linked machines, but it never asks for sudo, system files, new accounts, services, or SSH setup, and it explicitly forbids creating SSH access or discovering credentials.

Issues (3)

W011
MEDIUM

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

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

W013
MEDIUM

Attempt to modify system services in skill instructions.

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 17, 2026, 07:45 PM
Issues
3