imessage

Warn

Audited by Snyk on Apr 6, 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 shows the agent directly ingesting and acting on user-generated iMessage content (e.g., sdk.on('new-message' ...) that reads message.text and feeds it into processing/LLM flows) and also exposes messages via Photon Webhook, MCP tools, and the HTTP proxy—clear sources of untrusted third-party input that can influence tool use and decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 6, 2026, 03:54 PM
Issues
1
Security Audit — snyk — imessage