related-skill

Warn

Audited by Snyk on Apr 16, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). This skill's workflow explicitly searches for and installs skills from the public inference.sh registry (see Quick Start commands like "npx skills search" / "npx skills add" and the inference.sh/explore link in SKILL.md), so it ingests community-hosted, untrusted skill metadata/packages that can change the agent's tools and behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 16, 2026, 12:28 PM
Issues
1