cove-tts@r1
CAUTION· install onlyPublisher claims: "Enables AI clients to turn text into synthesized speech through a remotely hosted GPT-SoVITS model, returning a signed, time-limited audio link that can be played or downloaded. Supports Chinese and English text with your own reference audio for voice and tone." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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: 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
MCP_API_KEYConfiguration, not credentials: _CUDA_VISIBLE_DEVICES, API_V2_PID, CUDA_VISIBLE_DEVICES, LOCAL_RANK, MASTER_ADDR, MASTER_PORT, PUBLIC_BASE_URL, REF_AUDIO_PATH, REF_AUDIO_URL, REF_PROMPT_LANG, REF_PROMPT_TEXT, USE_LIBUV- Where it talks to
- no vendor host named in the codeAlso arxiv.org, huggingface.co, doi.org, python.org, shields.io, yuque.com, hf.space, fbaipublicfiles.com — 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 arxiv.org, huggingface.co, doi.org, python.org, shields.io, yuque.com, hf.space, fbaipublicfiles.com as well as its own vendor. The guard injects MCP_API_KEY 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 cove-tts@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 2026-11-16 and scored it 75/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Destructive file system command detected; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
rm /tmp/G2PWModel.zipFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.from .env import AttrDictFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.RUN sh /tmp/download_models.sh && rm /tmp/download_models.shFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.kill "$API_PID" "$TAIL_PID" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.RUN chmod +x /app/start.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.# 子进程退出后、被 wait 回收前会变成僵尸,kill -0 对僵尸仍然返回成功,Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.&& rm -rf /var/lib/apt/lists/*Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.process = subprocess.Popen(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.kill "$MCP_PID" "$API_PID" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.kill "$TAIL_PID" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.kill "$TAIL_PID" 2>/dev/null || trueFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.…,但是对高频重的板式混响去不干净。": "(234)DeEcho:Gecikme etkilerini giderir. Aggressive, Normal'dan daha kapsamlı bir şekilde giderir, DeReverb ek olarak yankıyı giderir, tek kana…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.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.
What would make this Verified
5 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim sue1231511: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.