Caveat verdict

opencode-acp-control

opencode-acp-control-v2

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Receives external input AND executes processes

Controls OpenCode via the Agent Client Protocol by spawning background processes and sending JSON-RPC messages; all operations are local process management for the stated purpose of orchestrating coding sessions.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

40
security
80
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination critical

Receives external input AND executes processes — the shape of a command & control channel

LLM05 · LLM06 · ASI10

Findings (1)

Pattern match high

Uses exec() — may execute shell commands

SKILL.md · code · exec(

Permissions & capabilities

No declared permissions — minimal attack surface.

process_execdata_encodingnetwork_in
Check another skill Browse the registry Auditing your own skills or configs? Use the API