integrate-skill
Warn
Audited by Snyk on Feb 25, 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 explicitly instructs the agent to ingest and read source skills from external repositories or a "repo URL" (see "Step 1: Ingest the Source Skill" and the "Source: [path or repo URL]" template), meaning the agent will parse arbitrary third-party content which can materially influence subsequent decisions and tool invocations.
Audit Metadata