self-improvement
Warn
Audited by Snyk on Mar 5, 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). Yes — SKILL.md explicitly instructs the agent to "Study open source projects" and cites public GitHub repos (References: https://github.com/actionbook/actionbook and https://github.com/accomplish-ai/accomplish), which implies fetching and interpreting public, user-generated repository content that can influence the agent's decisions and actions.
Audit Metadata