Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed XHunt trend-summary helper that browses public tweet-ranking pages and does not include code execution, credential access, hidden persistence, or exfiltration behavior.
Install only if you want a Chinese-output helper for XHunt trend summaries. Be aware it may browse XHunt when you ask broadly for hot posts or tweet summaries, and check the rsync install path before running the README command because --delete affects files inside the target skill directory.
The changelog states the skill "Enforces stable 3-line output per item with Chinese summaries," which describes a language constraint. Forcing a specific language without indicating user choice or opt-in is a natural-language policy concern under the language/locale rule.
The README states that the skill 'returns structured Chinese summaries,' which imposes a specific language by default. Under the policy, forcing a language or locale without explicit user choice or justification is a natural-language policy violation.
The README presents trigger examples such as '给我热门帖子链接+摘要' and '四小时最火帖子' that are generic natural-language requests and could collide with ordinary conversation rather than a narrowly scoped skill invocation. The section also gives only examples, not explicit constraints or negative examples that clarify when this skill should or should not activate.
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
mkdir -p ~/.openclaw/workspace/skills/xhunt-hot-tweets
rsync -a --delete ./xhunt-hot-tweets-skill/ ~/.openclaw/workspace/skills/xhunt-hot-tweets/
openclaw skills info xhunt-hot-tweets
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
mkdir -p ~/.openclaw/workspace/skills/xhunt-hot-tweets
rsync -a --delete ./xhunt-hot-tweets-skill/ ~/.openclaw/workspace/skills/xhunt-hot-tweets/
openclaw skills info xhunt-hot-tweets
该 README 是 markdown 文件，适用 SQP-1。L42-L44 给出的触发示例如“给我热门帖子链接+摘要”“四小时最火帖子”属于常见日常表达，且未说明明确的触发边界、限定上下文或负面示例，容易与普通对话请求重叠。
The skill description contains many broad, everyday trigger phrases such as '最火推文', '热门帖子', 'Top20', and '给我链接+摘要', which can match ordinary user requests that do not clearly intend to invoke this specific skill. This can cause unintended activation, leading the agent to browse external content and return synthesized summaries when the user may have meant something else, increasing the risk of confusion, overcollection, or unnecessary external access.
The manifest states the skill returns "structured Chinese summaries," which imposes a specific language in the skill behavior. This is a natural-language policy concern because the file does not indicate user opt-in, language selection, or a region-specific justification for requiring Chinese output.
No suspicious patterns detected.