search-messages
Warn
Audited by Snyk on Apr 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). This skill explicitly searches and returns Telegram chat messages (user-generated, untrusted content) as shown in SKILL.md ("Search Telegram Messages" and the send.py search examples), so the agent will ingest third-party chat content that could contain instructions influencing behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata