70High
The x-publisher skill is vulnerable to
Behavior Analysis
Description verified — behavior matches claim
Claims to do
X (Twitter) 推文发布工具: 使用官方 Tweepy 库发布推文，支持纯文本、图片、视频等多种媒体类型。
Actually does
This skill uses `python3` and the `tweepy` library to interact with the X (Twitter) API. It reads X API credentials from environment variables and allows users to publish text-only tweets or tweets with local image/video files. It also provides a `verify` command to check API credentials and returns tweet IDs and URLs upon successful publication.
Skill Info
Namemanifoldor/x-publisher
Registryclawhub
Version1.0.6
PURLpkg:clawhub/manifoldor/x-publisher@1.0.6
Stars4
Downloads1,837
Installs3
Source
SHA-2561b1d8829e23d...
SHA-16409ae652a89...
MD57181eb9e0b0f...
TLSH97d1ea91ef00...
ssdeep96:tX4RJuD9a...
Size6,573 bytes
Install
This skill has been flagged as potentially malicious. Review the findings below before installing.
ClawHubDocs
openclaw skills install manifoldor/x-publisherAssessments (2)
AI Agent Traps ↗Prompt Injection Detectedhighprompt injection
DeBERTa classifier detected prompt injection (confidence: 0.83)
83% confidence
Potential Command Injection via Script Argumentshighcommand execution
The skill describes executing an external Python script (`scripts/x_publisher.py`) with arguments (`text`, `--media`) that can be controlled by an attacker. If the underlying script does not properly sanitize these inputs, it could lead to arbitrary command injection.
80% confidenceline 80
python3 scripts/x_publisher.py tweet "Hello, X! This is my first tweet."
Data Exfiltration via Media Publishinghighdata exfiltration
The skill enables publishing local media files to a public platform (X) by specifying a file path via the `--media` argument. An attacker could manipulate an agent to provide a path to a sensitive local file, leading to its exfiltration.
90% confidenceline 87
python3 scripts/x_publisher.py tweet "Check out this photo!" --media /path/to/image.jpg
Badge
Markdown
[](https://mondoo.com/ai-agent-security/skills/clawhub/manifoldor/x-publisher)HTML
<a href="https://mondoo.com/ai-agent-security/skills/clawhub/manifoldor/x-publisher"><img src="https://mondoo.com/ai-agent-security/api/badge/clawhub/manifoldor/x-publisher.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/clawhub/manifoldor/x-publisher.svgSecure your AI agents
Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.
- Continuous scanning of skills across all registries
- Policy enforcement before skills reach your agents
- Integration with your existing security workflow