Skills/npm/claw-orchestrator

claw-orchestrator@7.21.4

CAUTION· startup only

Publisher claims: "Claw Orchestrator — run Claude Code, Codex, Antigravity, Grok Build, OpenCode, any ACP agent and custom coding CLIs as one unified runtime. Drop into Hermes Agent, Claude Desktop, Cursor, Cline, Continue, Zed, Windsurf, Goose or any Model Context Protocol" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher enderfga · publishing for 194 daysInstalls 6,934Last detonated 3d ago
What would fix thisWatchDispute verdict

Coverage

Startup only; authenticated tool behavior not tested.
Tested
server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
Not tested
the tool list (the server exited before answering) · what the tools do when called with real credentials

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
ANTHROPIC_API_KEYCLAWO_AUTH_TOKENGEMINI_API_KEYOPENAI_API_KEYOPENCLAW_SERVER_TOKENConfiguration, not credentials: AGY_BIN, ANTHROPIC_BASE_URL, AUTOLOOP_EMAIL_SCRIPT, AUTOLOOP_WECHAT_ACCOUNT, AUTOLOOP_WECHAT_RECIPIENT, AUTOLOOP_WHATSAPP_RECIPIENT, CLAUDE_BIN, CLAUDE_CODE_API_URL, CLAWO_ACP_MODEL, CLAWO_ACP_PERMISSION, CLAWO_API_URL, CLAWO_CHROME_BIN, CLAWO_CLAUDE_GATEWAY, CLAWO_MCP_TOOLS, CLAWO_NO_EMBEDDED_SERVER, CLAWO_RUNS_DIR, CLAWO_SESSIONS_DIR, CLAWO_WF_DIR, CODEX_BIN, CURSOR_BIN, GATEWAY_KEY, GATEWAY_URL, GEMINI_BIN, GROK_BIN, OPENAI_COMPAT_NEW_CONVO_HEURISTIC, OPENAI_COMPAT_SESSION_PREFIX, OPENAI_COMPAT_STATUS_URL, OPENAI_COMPAT_TOOLS_PER_MESSAGE, OPENAI_COMPAT_TURN_TIMEOUT_MS, OPENCLAW_CORS_ORIGINS, OPENCLAW_LOG_LEVEL, OPENCLAW_RATE_LIMIT, OPENCLAW_SERVE_MAX_SESSIONS, OPENCLAW_SERVE_TTL_MINUTES, OPENCLAW_SERVER_HOST
Where it talks to
no vendor host named in the code
What the honeypot saw
no credential files read · no network
What we could not test
the tool list (the server exited before answering) · what the tools do when called with real credentials

Connect it with a scoped credential, under the guard. It asks for ANTHROPIC_API_KEY, CLAWO_AUTH_TOKEN, GEMINI_API_KEY, OPENAI_API_KEY, OPENCLAW_SERVER_TOKEN and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.

$vet-skills run --net declared -- npx -y @enderfga/claw-orchestrator

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-11 and scored it 72/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Credential pass-through configuration; Credential pass-through configuration; Destructive file system command detected. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 53 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
32sprocessdependency install exit 0
52sclaimedstartup only: exited (0) before answering · solve [options] <task> Fix something and have the runtime check it: triage → implement → verify → repair until green fanout [options] <task> Ask several engines the same thing in parallel, optionally with a synthesis pass goal [options] [objective] Run a /goal on one thread (Codex or Claude Code), then have the runtime check
52sprocessscript backend runs setup only
52sprocessno install scripts to re-run

Static findings

MEDIUM
File type combined with upload actiondist/src/kernel/engine.js:1142 · File type combined with upload action — agent may exfiltrate local data filesartifacts.push({ nodeId, name: 'output.txt', body: result.output });Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Credential pass-through configurationdist/src/session-manager.js:819 · Credential pass-through configuration — agent relays sensitive credentials_proxyToken = null;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Credential pass-through configurationdist/src/session-manager.js:2544 · Credential pass-through configuration — agent relays sensitive credentialsthis._proxyToken = token;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
Process kill commanddist/src/session-manager.js:2740 · Process kill command — agent can terminate processes// Legacy format with no owner info — too risky to kill if a hostFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Destructive file system command detecteddist/src/session-manager.js:1005 · Destructive file system command detected// Starts a local proxy server that converts Anthropic → OpenAI formatFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/src/session-manager.js:2620 · Process kill command — agent can terminate processes// they're orphans and kill them. Read-merge-write keyed by ownerPid.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actiondist/bin/cli.js:1013 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(`\n${node.output}`);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commanddist/src/session-manager.js:2765 · Process kill command — agent can terminate processes/* individual kill failed */Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/src/engine-spawn.js:130 · Process kill command — agent can terminate processes/* fall through to a plain kill */Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commanddist/src/session-manager.js:2723 · Process kill command — agent can terminate processes// owned by another live manager. Only kill if owner is dead or unknownFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddist/src/session-manager.js:2759 · Process kill command — agent can terminate processes/* group kill failed */Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Collapsed <details> block carrying instructionsREADME.md:159 · Collapsed <details> block carrying instructions<summary><b>How the table stays current</b></summary> The versions above are what the weekly sweep last ran. `scripts/sweep.ts` measures each core engine's instFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Credential pass-through configurationdist/src/session-manager.js:2048 · Credential pass-through configuration — agent relays sensitive credentialsthis._proxyToken = null;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Credential pass-through configurationdist/src/session-manager.js:2435 · Credential pass-through configuration — agent relays sensitive credentialsreturn this._proxyToken ? `http://127.0.0.1:${port}/${this._proxyToken}` : `http://127.0.0.1:${port}`;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
MEDIUM
File type combined with upload actiondist/bin/cli.js:334 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(result.output);Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commanddist/src/mcp-annotations.js:11 · Process kill command — agent can terminate processes// destructive — irreversible side-effects (delete worktree, drop branch, kill process)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File type combined with upload actiondist/src/session-manager.js:3600 · File type combined with upload action — agent may exfiltrate local data filesconst artifacts = ['directive.json', 'eval_output.json', 'coder_summary.txt', 'diff.patch'];Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actiondist/bin/cli.js:624 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(r.output || 'Sent');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈105 tok
1 file · 81 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for @enderfga/claw-orchestrator@7.21.4 as of 3d ago. This is the package itself, not its dependencies.

What would make this Verified

8 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim enderfga: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  3. Credential pass-through configuration≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  6. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim enderfgaPropose a patch to the maintainer