Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

acp-router

v1.0.0

Route plain-language requests for Pi, Claude Code, Codex, OpenCode, Gemini CLI, or ACP harness work into either OpenClaw ACP runtime sessions or direct acpx-...

0· 363·2 current·2 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for zch-danny/openclaw-acp-router.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "acp-router" (zch-danny/openclaw-acp-router) from ClawHub.
Skill page: https://clawhub.ai/zch-danny/openclaw-acp-router
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install openclaw-acp-router

ClawHub CLI

Package manager switcher

npx clawhub@latest install openclaw-acp-router
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Suspicious
medium confidence
!
Purpose & Capability
The skill name/description (route ACP harness requests) aligns with the runtime behavior (choose ACP runtime or call acpx), but the SKILL.md instructs file access (./extensions/acpx/package.json), installs (npm install), and gateway restarts that go beyond simple routing. The metadata declares no required binaries/env/config paths, which is inconsistent with the actual needs.
!
Instruction Scope
Runtime instructions explicitly tell the agent to read local package.json, verify/install a plugin-local acpx, run exec commands that call acpx, and restart the gateway — these are file reads/writes, arbitrary shell executions, and system actions unrelated to mere message routing. The skill also references ${ACPX_CMD} and specific extension paths even though none are declared in metadata.
!
Install Mechanism
There is no declared install spec (instruction-only), but the SKILL.md requires running npm install in a local extension directory and verifying node/npm-acpx artifacts. Because the skill asks the agent to download and install packages at runtime, it effectively performs installs even though none are declared; that increases risk and should be explicitly stated and scoped.
!
Credentials
Metadata lists no required env vars, yet the instructions use and set ${ACPX_CMD} and expect node/npm to be present. The skill also expects access to extension paths (./extensions/acpx) and permission to modify them. The lack of declared env/config requirements is disproportionate to the real environment access the instructions demand.
Persistence & Privilege
The skill does not request 'always' or system-wide privileges, but it instructs modifying local extension artifacts and restarting the gateway. Those actions grant it effective persistence/impact on runtime behavior even without an 'always' flag; this is notable but not an explicit metadata privilege.
What to consider before installing
This skill's runtime instructions tell the agent to read and modify ./extensions/acpx, run node/npm commands, install acpx locally, execute shell commands, and restart the gateway — but the skill metadata doesn't declare the required binaries, env vars, or config paths. Before installing: (1) ask the publisher for source code or a homepage so you can audit what exact commands will run; (2) require the skill to declare required binaries (node, npm) and any env vars (ACPX_CMD) and config paths it will access; (3) run this skill in a sandboxed environment first, with backups of the extensions directory; (4) restrict its filesystem and process permissions if possible; (5) verify that any npm installs use pinned versions and come from a trusted package; and (6) do not allow it to restart production services without explicit confirmation. If the author provides explicit declarations and a trustworthy source, the concerns become easier to resolve.

Like a lobster shell, security has layers — review code before you run it.

acpvk97at03che8knyzz30jfwq3mbd82mc7zharnessvk97at03che8knyzz30jfwq3mbd82mc7zlatestvk97at03che8knyzz30jfwq3mbd82mc7zopenclawvk97at03che8knyzz30jfwq3mbd82mc7zroutervk97at03che8knyzz30jfwq3mbd82mc7z
363downloads
0stars
1versions
Updated 8h ago
v1.0.0
MIT-0

ACP Harness Router

When user intent is "run this in Pi/Claude Code/Codex/OpenCode/Gemini/Kimi (ACP harness)", do not use subagent runtime or PTY scraping. Route through ACP-aware flows.

Intent detection

Trigger this skill when the user asks OpenClaw to:

  • run something in Pi / Claude Code / Codex / OpenCode / Gemini
  • continue existing harness work
  • relay instructions to an external coding harness
  • keep an external harness conversation in a thread-like conversation

Mandatory preflight for coding-agent thread requests:

  • Before creating any thread for Pi/Claude/Codex/OpenCode/Gemini work, read this skill first in the same turn.
  • After reading, follow OpenClaw ACP runtime path below; do not use message(action="thread-create") for ACP harness thread spawn.

Mode selection

Choose one of these paths:

  1. OpenClaw ACP runtime path (default): use sessions_spawn / ACP runtime tools.
  2. Direct acpx path (telephone game): use acpx CLI through exec to drive the harness session directly.

Use direct acpx when one of these is true:

  • user explicitly asks for direct acpx driving
  • ACP runtime/plugin path is unavailable or unhealthy
  • the task is "just relay prompts to harness" and no OpenClaw ACP lifecycle features are needed

Do not use:

  • subagents runtime for harness control
  • /acp command delegation as a requirement for the user
  • PTY scraping of pi/claude/codex/opencode/gemini/kimi CLIs when acpx is available

AgentId mapping

Use these defaults when user names a harness directly:

  • "pi" -> agentId: "pi"
  • "claude" or "claude code" -> agentId: "claude"
  • "codex" -> agentId: "codex"
  • "opencode" -> agentId: "opencode"
  • "gemini" or "gemini cli" -> agentId: "gemini"
  • "kimi" or "kimi cli" -> agentId: "kimi"

These defaults match current acpx built-in aliases.

If policy rejects the chosen id, report the policy error clearly and ask for the allowed ACP agent id.

OpenClaw ACP runtime path

Required behavior:

  1. For ACP harness thread spawn requests, read this skill first in the same turn before calling tools.
  2. Use sessions_spawn with:
    • runtime: "acp"
    • thread: true
    • mode: "session" (unless user explicitly wants one-shot)
  3. For ACP harness thread creation, do not use message with action=thread-create; sessions_spawn is the only thread-create path.
  4. Put requested work in task so the ACP session gets it immediately.
  5. Set agentId explicitly unless ACP default agent is known.
  6. Do not ask user to run slash commands or CLI when this path works directly.

Example:

User: "spawn a test codex session in thread and tell it to say hi"

Call:

{
  "task": "Say hi.",
  "runtime": "acp",
  "agentId": "codex",
  "thread": true,
  "mode": "session"
}

Thread spawn recovery policy

When the user asks to start a coding harness in a thread (for example "start a codex/claude/pi/kimi thread"), treat that as an ACP runtime request and try to satisfy it end-to-end.

Required behavior when ACP backend is unavailable:

  1. Do not immediately ask the user to pick an alternate path.
  2. First attempt automatic local repair:
    • ensure plugin-local pinned acpx is installed in extensions/acpx
    • verify ${ACPX_CMD} --version
  3. After reinstall/repair, restart the gateway and explicitly offer to run that restart for the user.
  4. Retry ACP thread spawn once after repair.
  5. Only if repair+retry fails, report the concrete error and then offer fallback options.

When offering fallback, keep ACP first:

  • Option 1: retry ACP spawn after showing exact failing step
  • Option 2: direct acpx telephone-game flow

Do not default to subagent runtime for these requests.

ACPX install and version policy (direct acpx path)

For this repo, direct acpx calls must follow the same pinned policy as the @openclaw/acpx extension.

  1. Prefer plugin-local binary, not global PATH:
    • ./extensions/acpx/node_modules/.bin/acpx
  2. Resolve pinned version from extension dependency:
    • node -e "console.log(require('./extensions/acpx/package.json').dependencies.acpx)"
  3. If binary is missing or version mismatched, install plugin-local pinned version:
    • cd extensions/acpx && npm install --omit=dev --no-save acpx@<pinnedVersion>
  4. Verify before use:
    • ./extensions/acpx/node_modules/.bin/acpx --version
  5. If install/repair changed ACPX artifacts, restart the gateway and offer to run the restart.
  6. Do not run npm install -g acpx unless the user explicitly asks for global install.

Set and reuse:

ACPX_CMD="./extensions/acpx/node_modules/.bin/acpx"

Direct acpx path ("telephone game")

Use this path to drive harness sessions without /acp or subagent runtime.

Rules

  1. Use exec commands that call ${ACPX_CMD}.
  2. Reuse a stable session name per conversation so follow-up prompts stay in the same harness context.
  3. Prefer --format quiet for clean assistant text to relay back to user.
  4. Use exec (one-shot) only when the user wants one-shot behavior.
  5. Keep working directory explicit (--cwd) when task scope depends on repo context.

Session naming

Use a deterministic name, for example:

  • oc-<harness>-<conversationId>

Where conversationId is thread id when available, otherwise channel/conversation id.

Command templates

Persistent session (create if missing, then prompt):

${ACPX_CMD} codex sessions show oc-codex-<conversationId> \
  || ${ACPX_CMD} codex sessions new --name oc-codex-<conversationId>

${ACPX_CMD} codex -s oc-codex-<conversationId> --cwd <workspacePath> --format quiet "<prompt>"

One-shot:

${ACPX_CMD} codex exec --cwd <workspacePath> --format quiet "<prompt>"

Cancel in-flight turn:

${ACPX_CMD} codex cancel -s oc-codex-<conversationId>

Close session:

${ACPX_CMD} codex sessions close oc-codex-<conversationId>

Harness aliases in acpx

  • pi
  • claude
  • codex
  • opencode
  • gemini
  • kimi

Built-in adapter commands in acpx

Defaults are:

  • pi -> npx pi-acp
  • claude -> npx -y @zed-industries/claude-agent-acp
  • codex -> npx @zed-industries/codex-acp
  • opencode -> npx -y opencode-ai acp
  • gemini -> gemini
  • kimi -> kimi acp

If ~/.acpx/config.json overrides agents, those overrides replace defaults.

Failure handling

  • acpx: command not found:
    • for thread-spawn ACP requests, install plugin-local pinned acpx in extensions/acpx immediately
    • restart gateway after install and offer to run the restart automatically
    • then retry once
    • do not ask for install permission first unless policy explicitly requires it
    • do not install global acpx unless explicitly requested
  • adapter command missing (for example claude-agent-acp not found):
    • for thread-spawn ACP requests, first restore built-in defaults by removing broken ~/.acpx/config.json agent overrides
    • then retry once before offering fallback
    • if user wants binary-based overrides, install exactly the configured adapter binary
  • NO_SESSION: run ${ACPX_CMD} <agent> sessions new --name <sessionName> then retry prompt.
  • queue busy: either wait for completion (default) or use --no-wait when async behavior is explicitly desired.

Output relay

When relaying to user, return the final assistant text output from acpx command result. Avoid relaying raw local tool noise unless user asked for verbose logs.

Comments

Loading comments...