iris-development
Warn
Audited by Snyk on Jun 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). Outsider free text can enter the LLM context via the promotion worker:
add_session_eventenqueues a job, and the managed worker reads the session’scontent[].text(authored by the operating user’s end-users/other parties) and calls an LLM to extract durable facts.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata