nweii-skills
Warn
Audited by Snyk on May 15, 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). The SKILL.md explicitly instructs installing skills from a public GitHub repo (e.g., "From
agent-stuff(public)" with commands likebunx skills add nweii/agent-stuff`), which fetches SKILL.md and other user-authored skill files from an open/public source into the agent's ~/.claude/skills directory — untrusted third-party content that the agent will read and that can change its behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata