Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Vlmrun Cli Skill
v0.1.1Use the VLM Run CLI (`vlmrun`) to interact with Orion visual AI agent. Process images, videos, and documents with natural language. Triggers: image understanding/generation, object detection, OCR, video summarization, document extraction, image generation, visual AI chat, 'generate an image/video', 'analyze this image/video', 'extract text from', 'summarize this video', 'process this PDF'.
⭐ 2· 960·0 current·2 all-time
by@spillai
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The SKILL.md describes a vlmrun CLI for visual-AI tasks (image/video/doc processing) which is consistent with the skill name and description. However the repository/registry metadata lacks a homepage and source, so provenance is unclear.
Instruction Scope
Runtime instructions only tell the agent (or user) to create a venv, pip-install the 'vlmrun[cli]' package, set VLMRUN_* environment variables, and run 'vlmrun chat' to process files. The instructions do not direct the agent to read unrelated system files or exfiltrate data beyond uploading inputs to the service; they appear scoped to the stated purpose.
Install Mechanism
There is no formal install spec in the registry (instruction-only skill). SKILL.md recommends pip installing 'vlmrun[cli]' which is a common distribution method (moderate risk). The instructions contain an odd 'uv venv && source .venv/bin/activate' and 'uv pip install ...' usage — likely a typo or unknown helper tool; that ambiguity increases risk because it could lead to unexpected commands or behavior.
Credentials
Registry metadata declares no required environment variables, but SKILL.md explicitly requires VLMRUN_API_KEY (and optional VLMRUN_BASE_URL/CACHE_DIR). This mismatch is an incoherence: the skill will need an API key to operate, yet the declared requirements omit it. Asking for an API key for the service is reasonable, but the missing declaration and the instruction to 'load ./env' (which may contain secrets) are red flags you should verify before providing credentials.
Persistence & Privilege
The skill does not request always:true and is user-invocable with normal autonomous invocation allowed. It does not ask for system-wide config changes or other skills' credentials. No persistence concerns detected from the provided content.
What to consider before installing
This skill appears to be a CLI front-end for a VLM Run / Orion visual-AI service, which normally requires an API key. Before installing or providing secrets:
- Verify provenance: there is no homepage or source URL in the registry entry. Try to locate an official project page or PyPI package for 'vlmrun' and confirm the package author.
- Expect to supply VLMRUN_API_KEY: SKILL.md requires it, but the registry metadata omitted it — don't paste your API key into an env file or shell until you confirm the package origin.
- Check the install commands: SKILL.md uses 'uv' in 'uv venv' and 'uv pip install', which looks like a typo or an unknown helper; replace with standard commands (python -m venv .venv && source .venv/bin/activate; pip install 'vlmrun[cli]') or inspect the package before running.
- Prefer installing in an isolated environment (local virtualenv or sandbox) and review the PyPI package files for unexpected behavior before running commands that upload data.
If you can provide the skill's source or a link to the 'vlmrun' package, I can re-evaluate with higher confidence.Like a lobster shell, security has layers — review code before you run it.
latestvk97fwbb40hm755rsg6pnmzywah80x6hj
License
MIT-0
Free to use, modify, and redistribute. No attribution required.