optivibe-mcp@0.2.4
VERIFIED· not startedPublisher claims: "OptiVibe harness: ZOS-API automation, typed tools, and the single OptiVibe MCP" 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.
What changed since 0.2.3
vet-skills diff optivibe-mcp 0.2.3 0.2.4In the sandbox, this version reached for nothing 0.2.3 did not. Compared from the two recorded runs, not from source.
0.2.3 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
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 2026-11-19 and scored it 83/100 (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 · 1 s · 2 scenarios · 0 deviationsStatic findings
"""The ``zemax`` child's kill deadline, from production's own connect-timeout knob.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.completed = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.child = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.#: The sixth worker mode. Spawned ONLY after an --engine overall-deadline kill that saw anFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# thread exists to keep the parent alive, so it cannot become a way to kill it.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# first header cell becomes "design_name" and every design is mislabeled.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.#: deadline is a kill rather than a suggestion.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.to kill on either value. A real process's create_time is an epoch float, so ``0.0`` isFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.completed = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.``terminate_tracked`` REFUSES to kill on it), so a one-sided AccessDenied — realisticFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.sprint has been closing. One predicate, so doctor's proof gate and production's killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.#: Left below the parent's own 30 s kill so the grandchild's timeout is reportable.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.#: Doctor's own band for the ``zemax`` child's kill deadline. The operator'sFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.PID-reuse guard cannot prove identity, so we "never kill on doubt" ->Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.declared fail-safe. One predicate, so doctor's proof gate and production's kill gateFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.block or kill the engine, so a save or load is refused rather than hung.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# and we might kill an unrelated recycled PID. Never kill on unverifiableFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."engine or kill it.")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# filter the process snapshot to engine candidates — never as a kill key. AFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Reuses (L30 — the ONLY kill path / the ONLY atomic writer):Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.facts["find_spec_found"] = importlib.util.find_spec(facts["import_name"]) is not NoneFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.POLICY 1 ONLY (this cycle): a persistent, dead-parent-gated boot reap of a hard-killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Probe-grounded (BINDING). Claude Code's restart killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# engine SaveAs / LoadFile / New BLOCK (>100 s) or kill the engine; reads, an LDEFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.self._unresolved = {} # {pid: create_time} — parent unreadable; NO kill authorityFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.orphan. Policy 2 (stale LIVE-session reclaim) is DEFERRED (it would killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.evidence key ONLY — it is NEVER a kill key. A user's interactive OpticStudio isFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.full, a kill between the write and the newline) can still leave a torn FINAL line --Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.- ``process_reaper.terminate_tracked`` — every kill routes through it (its own baselineFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.which callers must treat as NOT ours (never kill an engine we cannot prove is ours).Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.user's engine is not. "Never kill on doubt."Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.spec = importlib.util.find_spec(top)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."engine or kill it.")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.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
No advisories in OSV for optivibe-mcp@0.2.4 as of 8 h ago. This is the package itself, not its dependencies.