opencode-plugins

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and modify external plugin source code, which constitutes untrusted data that could contain hidden instructions meant to influence the agent behavior. * Ingestion points: Plugin source (SKILL.md) * Boundary markers: Absent * Capability inventory: Code generation and modification * Sanitization: Absent
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 10:49 AM
Security Audit — agent-trust-hub — opencode-plugins