agora-reporting
Warn
Audited by Snyk on Jul 8, 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). The required workflow polls an Agora inbox and treats targeted human replies/comments/decisions/instructions as user input, so outsider-authored free text from a human on an external Agora server can be ingested into the agent’s LLM context via the
agoraCLI/inbox polling path whenAGORA_URLis set.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata