openclaim-mcp@r1

VERIFIED· install only

Publisher claims: "Provides AI clients with public breach-response guidance, scenario choices, official links, and blank inquiry, compensation, or mediation templates, while avoiding reading or returning personal data documents." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher baesic · publishing for 2 daysInstalls 0Last detonated 2d ago

$npx skills add openclaim-mcp

Watch Report an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.

Tested: every file read, file written and host contacted by what ran
Not tested: use of the skill by an agent

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: OPENCLAIM_MCP_TOKENConfiguration, not credentials: OPENCLAIM_TEST_BINARY
Where it talks to: no vendor host named in the codeAlso go.kr, or.kr, evil.invalid, example.invalid — 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: use of the skill by an agent

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names go.kr, or.kr, evil.invalid, example.invalid as well as its own vendor. The guard injects OPENCLAIM_MCP_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- <the server's command>

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

Is openclaim-mcp@r1 safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-12 and scored it 90/100 (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 · 1 scenarios · 0 deviations

t+CategoryObserved action

0.0sprocessno install scripts in bundle

0.0sprocessscript backend runs setup only

0.0sprocessno install scripts to re-run

Static findings

MEDIUM

Python subprocess execution detectedscripts/smoke-mcp.py:12 · Python subprocess execution detectedp = subprocess.Popen([binary], stdin=subprocess.PIPE, 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 detectedscripts/smoke-http.py:14 · Python subprocess execution detected

p = subprocess.Popen([binary,"--http"],env={**os.environ,"OPENCLAIM_MCP_TOKEN":token},stdout=subprocess.DEVNULL,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 detectedscripts/smoke-mcp.py:31 · Python subprocess execution detecteddescriptor = json.loads(subprocess.check_output([binary,"--describe"], text=True))Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.

AST05

Cost to the agent

Instructions loaded

≈1,818 tok

2 files · 46 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.