AGENT LAB: SKILLS

opencode-expert

Warn

Audited by Snyk on Feb 15, 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 explicitly exposes a webfetch tool in references/tools.md that can fetch and parse arbitrary web pages/URLs (e.g., "Fetch the README from GitHub"), meaning the agent will read untrusted public web/user-generated content and could be subject to indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:30 PM