skills/agentphone-ai/skills/agentphone/Snyk

agentphone

Warn

Audited by Snyk on Sep 5, 2026

Risk Level: MEDIUM

Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

Third-party content exposure detected (medium risk: 0.30). The agent skill provides tools to read SMS messages, WhatsApp messages, and voice call transcripts via the AgentPhone API and MCP, which can contain outsider-authored text from inbound messages and calls.

Issues (1)

W011

MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata

Risk Level

MEDIUM

Analyzed

Sep 5, 2026, 12:28 AM

Issues

1

Security Audit — snyk — agentphone