Skills/Glama/mediasense

mediasense@0.5.1

CAUTION· not started

Publisher claims: "Gives Claude ears and eyes for video and audio: summarize, explain, transcribe (word-level timestamps, ~99 languages) and edit TikTok, YouTube or Instagram links and local files. Runs locally with faster-whisper and FFmpeg." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher joaoestella · publishing for 6 daysInstalls 0Last detonated 6d ago
What would fix thisWatchDispute verdict

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 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: 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
HF_TOKEN or --hf-tokenConfiguration, not credentials: MEDIASENSE_API_MODEL, MEDIASENSE_CLAUDE_CONFIG, MEDIASENSE_COOKIES_FROM_BROWSER, MEDIASENSE_HOME, MEDIASENSE_TOOL_WAIT
Where it talks to
no vendor host named in the codeAlso ffmpeg.org, githubusercontent.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
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 ffmpeg.org, githubusercontent.com as well as its own vendor. The guard injects HF_TOKEN only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- <the server's command>

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 (3 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-08 and scored it 62/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Pipe-to-shell pattern; README links to an external installer; Collapsed <details> block carrying instructions. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 3 scenarios · 0 deviations
t+CategoryObserved action
0.2sprocessexited 1: /usr/bin/python3: No module named pip
0.3sprocessdependency install exit 1 ·
0.3sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.3sprocessscript backend runs setup only
0.4sprocesssecond launch, clock +45 days, CI unset
0.6sprocessexited 1: /usr/bin/python3: No module named pip

Static findings

MEDIUM
npx invocation of non-well-known package.github/workflows/release.yml:50 · npx invocation of non-well-known package — may execute untrusted codenpx -y @anthropic-ai/mcpb validate out/ext/manifest.jsonFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Python subprocess execution detectedsrc/mediasense/media.py:69 · Python subprocess execution detectedproc = subprocess.run(list(cmd), capture_output=capture, text=True, encoding="utf-8", errors="replace")Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
CRITICAL
Pipe-to-shell patterninstall.sh:3 · Pipe-to-shell pattern — downloads and immediately executes remote code# curl -LsSf https://raw.githubusercontent.com/joaoestella/mediasense/main/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
README links to an external installerREADME.md → https://github.com/joaoestella/mediasense/releases/latest/download/mediasense-skill.ziphttps://github.com/joaoestella/mediasense/releases/latest/download/mediasense-skill.zipFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Collapsed <details> block carrying instructionsREADME.md:85 · Collapsed <details> block carrying instructions<summary>As a Claude plugin (skill + server in one)</summary> The repository is also a Claude plugin: installing it adds both the mediasense tools and the skillFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Remote installer piped to shellinstall.sh:3 · Remote installer piped to shell# curl -LsSf https://raw.githubusercontent.com/joaoestella/mediasense/main/install.sh | shFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Collapsed <details> block carrying instructionsREADME.md:52 · Collapsed <details> block carrying instructions<summary>Prefer to read the script before running it?</summary> ```powershell irm https://raw.githubusercontent.com/joaoestella/mediasense/main/install.ps1 -OutFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known package.github/workflows/release.yml:51 · npx invocation of non-well-known package — may execute untrusted codenpx -y @anthropic-ai/mcpb pack out/ext out/mediasense.mcpbFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Privileged sudo commandinstall.sh:36 · Privileged sudo command — agent may execute with elevated privilegessudo pacman -S --noconfirm ffmpegFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Privileged sudo command.github/workflows/ci.yml:24 · Privileged sudo command — agent may execute with elevated privilegesrun: sudo apt-get update && sudo apt-get install -y ffmpegFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandinstall.sh:21 · Privileged sudo command — agent may execute with elevated privilegesecho "Python 3.10+ is required. macOS: brew install python · Ubuntu/Debian: sudo apt install python3 python3-venv"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Direct script execution from GitHub raw URLinstall.sh:3 · Direct script execution from GitHub raw URL — unverified code source# curl -LsSf https://raw.githubusercontent.com/joaoestella/mediasense/main/install.sh | shFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Privileged sudo commandinstall.sh:34 · Privileged sudo command — agent may execute with elevated privilegessudo dnf install -y ffmpegFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Privileged sudo commandinstall.sh:32 · Privileged sudo command — agent may execute with elevated privilegessudo apt-get update && sudo apt-get install -y ffmpegFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedtests/test_backends.py:120 · Python subprocess execution detectedsubprocess.run(["ffmpeg", "-y", "-v", "error", "-f", "lavfi", "-i", "anullsrc=r=48000:cl=stereo",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mediasense/setup.py:164 · Python subprocess execution detectedfirst = subprocess.run([ff, "-version"], capture_output=True, text=True).stdout.splitlines()[0]Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_understand.py:182 · Python subprocess execution detectedsubprocess.run(["ffmpeg", "-y", "-v", "error", "-f", "lavfi", "-i", "testsrc2=s=360x640:r=25:d=30",Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mediasense/setup.py:219 · Python subprocess execution detectedproc = subprocess.run([claude, "mcp", "get", SERVER_NAME], capture_output=True, text=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mediasense/setup.py:236 · Python subprocess execution detectedout = subprocess.run([smi], capture_output=True, text=True, timeout=20).stdoutFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mediasense/setup.py:114 · Python subprocess execution detectedsubprocess.run([claude, "mcp", "remove", "--scope", "user", SERVER_NAME], capture_output=True, text=True,Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/conftest.py:27 · Python subprocess execution detectedsubprocess.run(["ffmpeg", "-y", "-v", "error", *args], check=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/mediasense/setup.py:116 · Python subprocess execution detectedproc = subprocess.run(add, capture_output=True, text=True, timeout=60)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈1,361 tok
1 file · 46 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

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

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

18 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  2. Unclaimed publisher≈ +8 on the totalClaim joaoestella: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  4. README links to an external installer≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  5. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. Direct script execution from GitHub raw URL≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim joaoestellaPropose a patch to the maintainer