jiaojie
Warn
Audited by Snyk on Aug 26, 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 skill’s runtime “RECEIVE”/handoff handling ingests the user-supplied handoff content and attachments as untrusted data via
scripts/handoff.py receive <input>, which is free text authored by outsiders and parsed by the LLM/system at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata