cc-codex-mcp@0.1.0
VERIFIED· install onlyPublisher claims: "Enables Claude Code agents and subagents to get an independent read-only review of their changes from OpenAI Codex and to continue that same Codex conversation later for re-checks. Runs each request in an isolated CODEX_HOME so those threads stay separate from the Codex desktop app, supporting parallel callers and per-call model, effort, sandbox, and timeout settings." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 2 of 2 bundled scripts run with no arguments, with decoy credentials in the environment · 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
- 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
- use of the skill by an agent
Connect it under the guard. Bundled scripts ran with no arguments; no agent task scenario for this bundle. 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; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-18 and scored it 84/100 (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
// Wait for in-flight calls to kill their process trees (and release thread locks), but not forever.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell./** On shutdown, wait at most this long for in-flight tool calls to kill their Codex process trees. */Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.// Resolve after any in-flight kill finishes so no descendants outlive the call.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell./** Cancellation -> kill the process tree. */Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.assert.ok(!isUuid('../etc/passwd'));Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.// If stdio is still held open (e.g. kill failed for some descendant), don't hang forever.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.// Already settled (the kill finished after close/exit): no guard needed, and none must outlive the call.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.const kill = () => {Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.[mcp_servers.beta.http_headers]Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.Cost to the agent
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.