opencode-agents
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: 0.90). The skill explicitly enables and instructs agents to use webfetch to fetch public web content (e.g., assets/templates/security-auditor.json sets "webfetch": "allow" and assets/templates/prompts/security-auditor.txt / SKILL.md instruct the agent to "use webfetch to check for CVEs or security advisories"), so the agent will ingest and act on untrusted third‑party webpages that could carry indirect prompt injection.
Audit Metadata