dependency-confusion

Warn

Audited by Snyk on Nov 16, 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 recon step runs public registry lookups (npm view, pip dry-run, gem search --remote) on specific package names, which can return outsider-authored publisher metadata such as descriptions and summaries that the agent must actively query for, so exposure is low.

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 an offensive dependency-confusion playbook. It does not ask the agent to use sudo, create user accounts, or modify system or service configuration, though its PoC lifecycle hooks execute code on installing machines and it touches on publishing to public registries, so I score it moderately under the recall-first instruction.

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 16, 2026, 12:00 PM
Issues
2