ghost-audit-mcp@1.0.1
VERIFIED· not startedPublisher claims: "Enables MCP clients to deterministically audit claimed data-deletion requests, reconstruct what personal data remains reachable at a chosen cut-off, and retrieve evidence, case details, queues, what-if results, and verification outputs. It is read-only and lets agents build risk dashboards, review queues, case cards, and DPO briefs from the same capabilities as the CLI." 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 codeAlso python.org — not the publisher's domain; check what for before connecting.
- 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.
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 87/100 (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
subprocess.run([sys.executable, "-c", env_code], check=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.| C1 | Log file `log.txt` at the repo root, append-only, UTF-8 / `\n`, resolved relative to `AGENTS.md` | `log.txt` | `test_log_txt_entries_have_tool_and_model` |Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.return subprocess.run(["pdftotext", "-layout", str(p), "-"], capture_output=True, text=True).stdoutFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.* ``output.csv`` passes ``validate_output.py`` for that perturbed dataset;Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.subprocess.run([sys.executable, str(ROOT / "code" / "main.py"), "--out", str(out)], check=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.v = subprocess.run([sys.executable, str(VALIDATE), str(out)], env=env, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run([sys.executable, str(Path(__file__).resolve()), "cases", "--format", "json"],Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run([a.python, "-m", "build", "--outdir", str(out / "dist"), str(py)], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(ROOT / "code" / "ghost_mcp.py")], input="\n".join(json.dumps(r) for r in reqs) + "\nnot json\n",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(["npm", "pack", "--pack-destination", str(out)], check=True, cwd=npm)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out._tool("ghost_verify_output", "Verify output.csv", "Structural validation of output.csv (contract, vocabulary, ids, phase order) plus sha256 and status counts.",Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.return subprocess.run([sys.executable, str(CODE / "ghost_cli.py"), *args], capture_output=True, text=True, env=env)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run([sys.executable, str(MAIN), "--out", str(out)], env=env, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run(["tesseract", str(src), "stdout", "--psm", psm], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run([sys.executable, str(ROOT / "code" / "main.py"), "--out", str(out)], check=True, env=env,Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.errs = validate_output.validate(ROOT / "output.csv") if (ROOT / "output.csv").exists() else ["output.csv missing"]Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.subprocess.run([sys.executable, str(ROOT / "code" / "main.py")], check=True, capture_output=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.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.