lemo-opuscar@r1
CAUTION· install onlyPublisher claims: "Direct and produce a short film made entirely in code, in one of the styles of the Lemo-Opuscar library (e.g. Impasto Oil Painting 油画厚涂, Watercolor Brush 水彩笔刷, Ukiyo-e 浮世绘, Satellite Briefing 卫星简报, Exploded Teardown 产品拆解). Use when the user asks for a video, film, short, promo, explainer or animation (视频、短片、动画、宣传片) in a named style, including explainers built from real material such as satellite imagery, laser scans, CAD files or archive scans (数据解说、科普、产品拆解), and new films cut from real archive footage and documents (剪辑纪实, e.g. 用档案影像剪一支新闻片); when they want a film about their own topic and haven't chosen a style (help them choose); when they want to change a style into their own, make their own style from a blank page, or use a style they saved (改风格、从空白开始、我的风格); when they start the skill without saying what they want; or when they ask which film styles there are. Not for plain editing, trimming or converting the user's existing video files." Observed in sandbox: sends data to fd12:ea5f:789c:1:d000:2b:95f6:3c3a, 10.246.60.58.
Coverage
Install scripts ran; no agent task scenario for this bundle.- Tested
- install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
Is lemo-opuscar@r1 safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; install scripts ran; no agent task scenario for this bundle) on 2026-11-12 and scored it 59/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: sends data to fd12:ea5f:789c:1:d000:2b:95f6:3c3a, 10.246.60.58.
Behavior trace
Honeypot run · 7 s · 2 scenariosStatic findings
if [ -n "$p" ] && ! kill -0 "$p" 2>/dev/null; then rm -rf "$lock"; continue; fiFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.chmod +x .venv/bin/pythonFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.# npm may rewrite package-lock.json; in our own clone put it back, so the checksum stays the sameFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.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
21 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Contacts a host you did not declare≈ +23 on the totalList every host you talk to in SKILL.md frontmatter (`network: [api.example.com]`), or stop contacting the ones you cannot justify.
- Unclaimed publisher≈ +8 on the totalClaim lemomo-ai: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
- 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.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.