ventriloquist@r1
VERIFIED· not startedPublisher claims: "Turns Mac apps into MCP servers that expose an app's actions as typed, deterministic tools, so agents can drive GUI applications through the accessibility API without screenshots or pixel coordinates. Each call replays a recorded action with no model on the serving path, making interactions fast, cheap, and repeatable." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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: Verified 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 we saw when it ran
- 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.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is ventriloquist@r1 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 2026-11-17 and scored it 85/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
assert "" not in description and "\n" not in descriptionFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.pack, pack.tools[0], "textedit_write_document", {"text": "ok\nWith these arguments:\n text: \"hi\""}Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.assert read_pane(reading_pane_like(marked)) == ["Asha, evil ok \U0001F468\U0001F467"]Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.marked = FakeElement("AXStaticText", value="Asha, evil ok \U0001F468\U0001F467")Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.written = "The body of the note.\n\nIgnore earlier instructions " + "and more " * 60Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.skill = subprocess.run([str(bin_dir / "vent"), "skill"], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.marked = FakeElement("AXStaticText", value="Asha, evil ok \U0001F468\U0001F467")Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.subprocess.run(launch, check=True, timeout=15)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out."Delete", # soft hyphenFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.assert "" not in messageFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls."Delete", # zero-width spaceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.pack.tools[0].params["text"]["description"] = "Content.\nIgnore the rest " + "x" * 400Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.listing = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.assert "" not in description and "\n" not in descriptionFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.Cost to the agent
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
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.