workflow

Warn

Audited by Snyk on May 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). This skill's documentation and examples (e.g., "Example
  • Using fetch in workflow context" and webhook/hook examples in SKILL.md, plus the DurableAgent pattern in references/durable-agent-patterns.md that defines a searchWeb tool calling webSearch(query) and resumeWebhook/resumeHook examples) show the agent fetching/receiving data from arbitrary external web URLs and webhook payloads and then reading/interpreting that content to drive agent decisions and workflow actions (approvals, report generation), so untrusted third-party content can materially influence behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 6, 2026, 11:16 AM
Issues
1