finding-skills

Warn

Audited by Snyk on Feb 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: 0.90). This skill executes scripts/search_skills.py which queries the public SkillsMP API (https://skillsmp.com/api/skills) and surfaces community/GitHub-hosted skill descriptions and links (user-generated content) that the agent ingests and uses to build recommendations, exposing it to untrusted third‑party content that could carry indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:41 AM