ai-video-clip@2.0.0
VERIFIED· install onlyPublisher claims: "AI 智能视频剪辑助手。支持 ASR 语音转文字、词级时间戳剪切、LLM 驱动剪辑决策(EDL)、视频渲染、自检循环、多平台导出。当用户需要:自动剪辑视频、AI 理解视频内容并剪切、生成字幕并烧录、提取高光片段、导出短视频、多平台视频格式适配时使用此技能。" 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
Is [email protected] 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 2026-11-11 and scored it 87/100 (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 · 1 scenarios · 0 deviationsStatic findings
python3 scripts/self_eval.py --video edit/final.mp4 --edl edl.json --output quality_report.jsonFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.python3 scripts/cut_video.py --input video.mp4 --edl edl.json --output ./clips/Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.result = 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.result = 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.result = 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.python3 scripts/render_edl.py --edl edl.json --output edit/final.mp4Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.result = 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.return subprocess.run(cmd, capture_output=True, text=True).returncode == 0Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.return subprocess.run(cmd, capture_output=True).returncode == 0Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.python3 generate_edl.py --transcript transcript.json --strategy remove_fillers --output edl.jsonFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.result = 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.result = subprocess.run(cmd, capture_output=True, text=True)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.python3 render_edl.py --edl edl.json --output edit/ --segmentsFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.result = 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.result = 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.return subprocess.run(cmd, capture_output=True).returncode == 0Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(cmd, capture_output=True)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.result = 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.return subprocess.run(cmd, capture_output=True).returncode == 0Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(cmd, capture_output=True, text=True)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.result = subprocess.run(cmd, capture_output=True, text=True)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.python3 render_edl.py --edl edl.json --output edit/final.mp4Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.result = subprocess.run(cmd, capture_output=True, text=True)Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.result = 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.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.