VOVO超能数据分析师

PassAudited by VirusTotal on May 11, 2026.

Overview

Type: OpenClaw Skill Name: vovo-data-analyst Version: 1.0.8 The skill acts as a client for a remote data analysis service (vort-ai.com) and includes robust security checks in `scripts/main.py` to prevent the unauthorized upload of sensitive system files like SSH keys or `/etc/` configs. However, it is classified as suspicious due to aggressive prompt injection and 'agent hijacking' techniques found in `SKILL.md` and the output of `scripts/main.py`. The script explicitly prints a 'SYSTEM OVERRIDE' block intended to manipulate the host AI's tool-calling logic, forcing it to use specific UI components and forbidding standard file-reading actions, which subverts the host's autonomous control flow.

Findings (0)

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

Files and analysis instructions you choose may be processed outside your machine by the VOVO service.

Why it was flagged

The user's prompt and uploaded file IDs are sent to a remote VOVO super-agent for analysis.

Skill content
start_payload = {"appId": "1", "query": query, "files": file_ids, "is_network_enabled": True, "taskType": "analysis"}
Recommendation

Only use this skill with data you are comfortable sending to the configured VOVO service, and check the provider's privacy and retention terms.

What this means

The remote sandbox may use network access while analyzing your uploaded data.

Why it was flagged

The remote analysis task is explicitly launched with network access enabled, with no documented user option in the artifacts to disable it.

Skill content
"is_network_enabled": True
Recommendation

Avoid uploading highly sensitive files unless you trust the remote sandbox behavior; the publisher should document what remote network access is used for.

What this means

If VOVO_API_HOST is wrong or untrusted, the API token and uploaded files could be sent to that host.

Why it was flagged

The VOVO API token is read from the environment and sent as the authentication header to the configured API host.

Skill content
headers = {"vovo-key": VOVO_API_TOKEN}
Recommendation

Set VOVO_API_HOST only to the verified official HTTPS endpoint and keep VOVO_API_TOKEN scoped and revocable where possible.

What this means

Domain confusion can lead to misconfiguration or accidental disclosure of files and tokens to the wrong service.

Why it was flagged

The documentation references multiple related service domains for a skill that receives files and tokens, so users should verify which endpoint is official.

Skill content
访问 VOVO 官方网站 (synvort.com) ... export VOVO_API_HOST="https://api.vort-ai.com"
Recommendation

Confirm the official VOVO domain and API host from a trusted source before configuring credentials.

What this means

Users may over-trust the remote service's data handling based on claims that cannot be verified from the local artifacts alone.

Why it was flagged

The artifact makes service-level privacy and retention assurances that are not locally enforceable by the included script.

Skill content
阅后即焚:云端代码沙盒在完成运算并返回报告/图表后,会自动销毁临时执行环境。
Recommendation

Treat remote retention and deletion claims as provider policy claims, and verify them before uploading confidential data.