arabic-siri
Warn
Audited by Snyk on Nov 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow sends the user's own spoken Arabic command to the local Hermes chat API, and Hermes may then fetch outsider-authored web content, such as news results for the "آخر أخبار التقنية" example, which the agent must actively search for and is not forced to ingest.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata