open-source-contributions
Warn
Audited by Snyk on Feb 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to fetch and read public repository content and user-generated discussion (e.g., CONTRIBUTING.md, CODE_OF_CONDUCT.md, PULL_REQUEST_TEMPLATE.md, LICENSE and issue/maintainer comments on GitHub or other public project URLs), which are untrusted third-party sources the agent must interpret as part of its workflow.
Audit Metadata