signal

Warn

Audited by Snyk on Mar 1, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill ingests and uses incoming Signal messages and group history (e.g., "Group history context uses channels.signal.historyLimit" and DM/group handling via signal-cli) — untrusted, user-generated third‑party content — as runtime context that can influence replies, reactions, and downstream actions described in the workflow (Group Chat Safeguards, Sending Messages, Reactions), so it can enable indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 01:51 PM