claude-handoff
Warn
Audited by Snyk on Aug 19, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The required runtime workflow in SKILL.md only summarizes the current conversation and seeds a new background agent with that summary as a prompt, which is user-authored content that can include indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata