code-refactor
Warn
Audited by Snyk on Mar 3, 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 instructs using "WebSearch/WebFetch" to research idiomatic refactoring patterns in SKILL.md (and SUBAGENT.md delegates a code-researcher agent), meaning it fetches and ingests untrusted public web content that will be interpreted and can materially influence refactoring decisions.
Audit Metadata