video-recap@2.0.1
VERIFIED· install onlyPublisher claims: "General-purpose AI video editing and narration recap skill powered by minimal atomic CLIs (Python stdlib + ffmpeg/ffprobe) and a single canonical timeline.json. Supports multi-source cutting, multimodal frame inspection, local-first ASR/TTS (with optional remote HTTP ASR/TTS), multi-track ducking & loudness, subtitles, vertical packaging & SFX, JianYing draft export, review dashboard, and asset library. 通用视频剪辑与解说制作技能:用极简原子 CLI 与单一 timeline.json 完成多源剪辑、看图选镜、配音混音、字幕包装、物理质检及剪映导出。" 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 13 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 changed since 1.0.23
vet-skills diff video-recap 1.0.23 2.0.1This version reaches for something 1.0.23 did not: 3 new credential variables (ASR_API_KEY, FISH_AUDIO_API_KEY, OPENAI_API_KEY). Compared from the two recorded runs, not from source.
- New credential variables
- ASR_API_KEY, FISH_AUDIO_API_KEY, OPENAI_API_KEY
- No longer contacted
- xiaomimimo.com
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; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-22 and scored it 88/100 (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 · 1 s · 2 scenarios · 0 deviationsStatic findings
result = subprocess.run(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, encoding="utf-8", errors="replace", timeout=30).returncode == 0 and out_path.is_file()Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.result = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.npx = shutil.which("npx")Fix: Pin versions and sources; vendor anything fetched at install time.return subprocess.run(cmd, capture_output=True, text=True, encoding="utf-8", errors="replace", timeout=20).returncode == 0 and out_path.is_file()Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.plates, and Node/npx Remotion for transparent ProRes 4444 / VP9 animated overlays.Fix: Pin versions and sources; vendor anything fetched at install time.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.