flow-discover

Warn

Audited by Snyk on May 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). Yes — the skill explicitly invokes live web research (Perplexity live web search) and launches orchestrate.sh probe/probe-single and CLI providers that fetch and return external URLs/content (see "Perplexity
  • Live web search" and the "When discover workflow fetches external URLs..." / security framing sections), which the agent is required to read and synthesize into decisions, so untrusted third‑party content can materially influence actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 9, 2026, 06:34 AM
Issues
1