security-gate
Warn
Audited by Snyk on Apr 9, 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). The skill's SKILL.md explicitly ingests and evaluates the
messageinput (raw inbound Telegram user text), which is untrusted user-generated content that the agent must read and which can influence whether the message is forwarded to Claude, enabling indirect prompt-injection risks.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata