opencode-controller

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is designed to invoke the opencode binary and interact with it using various slash commands, including /sessions, /agents, and /models, to control the tool's behavior and environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data originating from the Opencode tool, creating an attack surface for indirect prompt injection.
  • Ingestion points: The agent is instructed to read and review plans, task analyses, and clarification questions provided by the Opencode tool (referenced in SKILL.md and assets/operator-prompts.md).
  • Boundary markers: There are no specific delimiters or instructions provided to the agent to treat external tool output as data rather than instructions.
  • Capability inventory: The skill possesses command execution capabilities within the opencode environment, which are driven by the plans it ingests.
  • Sanitization: The instructions do not mandate any filtering, escaping, or validation of the content received from the tool before the agent acts upon it or presents it to the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 04:08 PM