Skills/PyPI/orchestrator-mcp-server

orchestrator-mcp-server@0.12.0

CAUTION· not started

Publisher claims: "Let one coding-agent CLI consult another through Codex, Claude Code, OpenCode, GitHub Copilot, or Antigravity." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher crak1644 · publishing for 104 daysInstalls 334Last detonated 9 h ago
What would fix thisWatchDispute verdict

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

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
no credential variables read in the code
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
server startup · the tool list · tool behavior

Connect it under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- uvx orchestrator-mcp-server

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; not started: dependency install failed; the server itself was not observed) on 2026-11-14 and scored it 79/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Collapsed <details> block carrying instructions. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedsmoke_workflow_live.py:180 · Python subprocess execution detecteddone = subprocess.run(argv, cwd=repo, input=text, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Access to sensitive file pathstests/sandbox/test_escapes.py:245 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files`~/.netrc` and `~/.git-credentials` are plaintext passwords in a file, and a workerFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedsmoke_workflow_live.py:135 · Python subprocess execution detecteddone = subprocess.run(["git", *args], cwd=repo, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Privileged sudo command.github/workflows/release.yml:44 · Privileged sudo command — agent may execute with elevated privilegessudo apt-get install -y bubblewrapFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandtests/sandbox/test_escapes.py:231 · Process kill command — agent can terminate processesconfined process could not kill a process it had started itself. Which breaks anyFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Privileged sudo command.github/workflows/test.yml:37 · Privileged sudo command — agent may execute with elevated privilegessudo apt-get updateFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/fixtures/fake_cli.py:60 · Python subprocess execution detectedgrandchild = subprocess.Popen([sys.executable, "-c", "import time; time.sleep(300)"])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Collapsed <details> block carrying instructionsREADME.md:278 · Collapsed <details> block carrying instructions<summary><strong>VS Code, Cursor</strong></summary> <br> VS Code reads `.vscode/mcp.json` in the workspace; Cursor reads `~/.cursor/mcp.json` with the same entrFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedsmoke_workflow_live.py:203 · Python subprocess execution detecteddone = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Privileged sudo command.github/workflows/release.yml:43 · Privileged sudo command — agent may execute with elevated privilegessudo apt-get updateFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/fixtures/fake_cli.py:50 · Python subprocess execution detectedgrandchild = subprocess.Popen([sys.executable, "-c", "import time; time.sleep(300)"])Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Privileged sudo command.github/workflows/test.yml:74 · Privileged sudo command — agent may execute with elevated privilegessudo apt-get install -y bubblewrapFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Privileged sudo command.github/workflows/release.yml:45 · Privileged sudo command — agent may execute with elevated privilegessudo sysctl -w kernel.apparmor_restrict_unprivileged_userns=0 || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Privileged sudo command.github/workflows/test.yml:39 · Privileged sudo command — agent may execute with elevated privilegessudo sysctl -w kernel.apparmor_restrict_unprivileged_userns=0 || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandtests/fixtures/fake_cli.py:58 · Process kill command — agent can terminate processes# group leader is gone and reaped by the time anything tries to kill it, so aFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandtests/sandbox/test_escapes.py:237 · Process kill command — agent can terminate processesscript = 'sleep 30 & child=$!; kill -TERM "$child"; wait "$child"; echo REAPED'Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/sandbox/conftest.py:79 · Python subprocess execution detecteddone = subprocess.run(argv, capture_output=True, text=True, timeout=60, **kwargs)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
References a credential file in the home directorytests/sandbox/test_escapes.py:249 · References a credential file in the home directoryprofile's shape, and a test that needed a real `~/.netrc` to exist would be skippedFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Privileged sudo command.github/workflows/test.yml:38 · Privileged sudo command — agent may execute with elevated privilegessudo apt-get install -y bubblewrapFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/sandbox/test_escapes.py:216 · Python subprocess execution detectedvictim = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/sandbox/test_escapes.py:115 · Python subprocess execution detectedunconfined = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Privileged sudo command.github/workflows/test.yml:73 · Privileged sudo command — agent may execute with elevated privilegessudo apt-get updateFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Access to sensitive file pathstests/sandbox/test_escapes.py:249 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesprofile's shape, and a test that needed a real `~/.netrc` to exist would be skippedFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
References a credential file in the home directorytests/sandbox/test_escapes.py:245 · References a credential file in the home directory`~/.netrc` and `~/.git-credentials` are plaintext passwords in a file, and a workerFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
File permission modification commandtests/sandbox/test_escapes.py:57 · File permission modification command — agent changes file ownership/permissionsassert attempt(f'chmod 777 "{target}"', worktree).returncode != 0Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
Process kill commandtests/sandbox/test_escapes.py:220 · Process kill command — agent can terminate processesdenied = attempt(f"kill -TERM {victim.pid}", worktree, start_new_session=True)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandtests/test_sandbox.py:620 · Process kill command — agent can terminate processesread a *successful* kill as a denial whenever the victim outlived a two-secondFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
GitHub token pattern detectedtests/test_review_secrets.py:34 · GitHub token pattern detected — possible hardcoded or harvested tokenOTHER = "ghp_AAAABBBBCCCCDDDDEEEEFFFFGGGGHHHHIIII"Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
MEDIUM
Access to sensitive file pathstests/test_copilot_adapter.py:764 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files["", "not-a-uuid", "../../etc/passwd", "ses_01e1d1c6effevvnIR8XBZ9hlqX", UNKNOWN_SESSION],Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedtests/test_consult_store.py:1294 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_review_diff_ref.py:149 · Python subprocess execution detectedsubprocess.run(["git", "diff", "topic", "main"], cwd=repo, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Process kill commandtests/test_consult_config.py:305 · Process kill command — agent can terminate processesreads as "no limit" and behaves as "kill it immediately"."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_workflow_service.py:214 · Python subprocess execution detectedsubprocess.run(["git", "add", "-A"], cwd=path, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Refusal suppressionREADME.md:1322 · Refusal suppression — attempting to prevent safety responses · informational: not an instruction fileA consultation with no turns yet is never refused. Nothing has been spent on it, soFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedtests/test_review_diff_ref.py:333 · Python subprocess execution detectedsubprocess.run(["git", "diff", "HEAD~1", "HEAD"], cwd=trap, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Destructive file system command detectedtests/test_codex_adapter.py:236 · Destructive file system command detected{"type": "item.started", "item": {"type": "command_execution", "command": "rm -rf /"}},Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Bidirectional text override characters detectedtests/test_search.py:215 · Bidirectional text override characters detected — may hide content direction"a\x00b", "\x1b[31m", "é", "‮", "x " * 100, "a" * 200,Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedtests/test_workflow_service.py:405 · Python subprocess execution detectedhead = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_workflow_service.py:215 · Python subprocess execution detectedsubprocess.run(["git", "commit", "-qm", "first"], cwd=path, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Auto-update or dynamic fetch configurationtests/snapshot.py:3 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeDeliberately a separate command rather than an auto-update flag on the test. AFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedtests/test_sandbox.py:92 · Python subprocess execution detectedreturn subprocess.run(argv, capture_output=True, text=True, timeout=60, **kwargs)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_code_execution.py:634 · Python subprocess execution detectedsubprocess.run(["git", "init", "-q"], cwd=decoy, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_consult_store.py:335 · Python subprocess execution detectedopeners = [subprocess.Popen(args, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_workflow_service.py:1121 · Python subprocess execution detectedsubprocess.run(["git", "commit", "-aqm", "round one"], cwd=repo, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Destructive command against a filesystem root or devicetests/test_codex_adapter.py:236 · Destructive command against a filesystem root or device{"type": "item.started", "item": {"type": "command_execution", "command": "rm -rf /"}},Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_code_execution.py:103 · Python subprocess execution detectedsubprocess.run(["git", *args], cwd=path, check=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_workflow_service.py:211 · Python subprocess execution detectedsubprocess.run(command, cwd=path, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_code_execution.py:216 · Python subprocess execution detectedlisted = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Access to sensitive file pathstests/test_sandbox.py:188 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""SBPL is last-match-wins. Reordering these two blocks unhides `~/.ssh` withoutFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
LOW
HTML comment carrying imperative instructions to the agentorchestrator_mcp/ui/view.html:2 · HTML comment carrying imperative instructions to the agent · informational: not an instruction fileThe MCP Apps view for a review or a workflow (ext-apps 2026-01-26). The host renders it in a sandboxed iframe and posts the tool result in; nothing here fetchesFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Stripe-like API key pattern detectedtests/test_consult_mcp.py:192 · Stripe-like API key pattern detected — possible hardcoded or harvested keyraise RuntimeError("database is locked; token=sk-live-abcdefghijkl")Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
MEDIUM
Python subprocess execution detectedtests/test_review_diff_ref.py:148 · Python subprocess execution detectedsubprocess.run(["git", "diff", "HEAD~1", "HEAD~2"], cwd=repo, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Access to sensitive file pathstests/sandbox/test_escapes.py:260 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filessecret = unmasked_root / "home" / ".netrc"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedtests/test_review_diff_ref.py:27 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Access to sensitive file pathstests/test_sandbox.py:828 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filessecret = tmp_path / "home" / ".netrc"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandtests/test_opencode_adapter.py:386 · File permission modification command — agent changes file ownership/permissions# back. The chmod is on the deepest directory in the chain, which the walk reachesFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
URL with embedded credentialstests/test_review_secrets.py:114 · URL with embedded credentials — may be phishing or credential leakingpytest.param("https://example.com:8080/path@x", id="a port is not a password"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07
MEDIUM
Python subprocess execution detectedtests/test_code_execution.py:120 · Python subprocess execution detecteddone = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_cli_entrypoint.py:89 · Python subprocess execution detecteddone = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈70 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 orchestrator-mcp-server@0.12.0 as of 8 h ago. This is the package itself, not its dependencies.

What would make this Verified

1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim crak1644: 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. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  4. Access to sensitive file paths≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. Privileged sudo command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  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 PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim crak1644Propose a patch to the maintainer