teamwork-mcp@0.3.3
CAUTION· install onlyPublisher claims: "SSE-based MCP Server and Client" 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
- 8 of 21 bundled scripts run with no arguments (the rest were not run: per-bundle cap), 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: Caution 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
DASHSCOPE_API_KEYGITHUB_TOKENTOKENIZERS_PARALLELISMConfiguration, not credentials: BROWSER_PROXY_SERVER- Where it talks to
- no vendor host named in the codeAlso arxiv.org, nih.gov, weather.com, searx.be, priv.au, scmor.com, aliyuncs.com, firecrawl.dev, people.com.cn — not the publisher's domain; check what for before connecting.
- What we saw when it ran
- 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 arxiv.org, nih.gov, weather.com, searx.be, priv.au, scmor.com, aliyuncs.com, firecrawl.dev, people.com.cn as well as its own vendor. The guard injects DASHSCOPE_API_KEY, GITHUB_TOKEN, TOKENIZERS_PARALLELISM only into requests to the host you bind (and its subdomains) and refuses the rest.
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 2026-11-19 and scored it 79/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: OS command execution function call detected; OS command execution function call detected. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 2 scenarios · 0 deviationsStatic findings
print(f"Failed to kill chrome: {e}")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.os.system('bash -c "source /home/headless/.bashrc && killer chrome"')Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.print(f"Failed to kill chrome: {e}")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.process.kill() # kill it with the hard way, process.terminate may timeout.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.os.system('bash -c "source /home/headless/.bashrc && killer chrome"')Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.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
No advisories in OSV for teamwork-mcp@0.3.3 as of 12 h ago. This is the package itself, not its dependencies.
What would make this Verified
1 point to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- OS command execution function call detected≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Unclaimed publisher≈ +8 on the totalClaim qingxu-fu-fuqingxu.fqx: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.