moldable

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). The skill explicitly provides agent tools to add/sync skill repositories from public sources (e.g., addSkillRepo with GitHub-style URLs and syncSkills that "Downloads selected skills to ~/.moldable/shared/skills/") and those instruction-based SKILL.md files are read/interpreted by the agent, exposing it to untrusted, user-provided repository content (third-party skills) that could carry indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:00 AM