analyze video by qwen

ReviewAudited by ClawScan on May 10, 2026.

Overview

The video-analysis function matches its description, but the skill includes broad local Python and chmod command permissions that are wider than the documented analyzer command.

Use this skill only if you are comfortable sending the selected videos and prompts to DashScope/Qwen and using your DashScope API key. Before installing, consider narrowing or removing the .claude Bash allow rules, especially the unrestricted python3 and chmod permissions, and pin the dashscope dependency.

Findings (4)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

If the agent or a later prompt misuses this permission, it could run local Python code or change file permissions unrelated to analyzing a video.

Why it was flagged

These permissions are not limited to scripts/analyze.py or the skill directory. They could allow arbitrary python3 execution or chmod changes beyond the documented video-analysis workflow.

Skill content
"allow": ["Bash(chmod:*)", "Bash(python3:*)"]
Recommendation

Remove the chmod allow rule unless needed, and scope Python permission to the exact analyzer command, such as running only scripts/analyze.py with user-provided arguments.

What this means

Analysis requests use the user's DashScope account and may consume quota or incur charges.

Why it was flagged

The script reads a DashScope API key from the user's OpenClaw config. This is expected for calling Qwen/DashScope, but it means the skill uses the user's provider credential.

Skill content
api_key = config.get("skills", {}).get("dashscope", {}).get("apiKey")
Recommendation

Use a dedicated DashScope key if possible, monitor usage, and avoid sharing ~/.openclaw/openclaw.json.

What this means

Local videos, remote video URLs, prompts, and resulting analysis may be processed by Aliyun DashScope/Qwen.

Why it was flagged

The selected video source and prompt are provided to the DashScope/Qwen API for analysis. This is the stated purpose, but it is an external provider data flow.

Skill content
dashscope.base_http_api_url = "https://dashscope.aliyuncs.com/api/v1" ... MultiModalConversation.call(api_key=api_key, model='qwen3.5-plus', messages=messages)
Recommendation

Only analyze videos you are comfortable sending to the provider, and review DashScope's data handling terms for sensitive content.

What this means

Dependency changes could alter behavior or introduce vulnerabilities even if the current skill code is simple.

Why it was flagged

The dependency is not version-pinned, so a future manual install could resolve to a different package version than the author tested.

Skill content
dashscope
Recommendation

Pin the dashscope version and install from a trusted package index before use.