T01 · Skill Instruction Hijacking
- Location
SKILL.md:18- Finding
Mandatory Branded Hashtag Injection into Generated Content
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This is mostly a social-content generation guide, but it hard-codes a branded hashtag into user-facing output, so it should be reviewed before installation.
Install only if you are comfortable reviewing or overriding generated tags before publishing. The main operational risk is not system compromise; it is that generated Xiaohongshu content may include the fixed #虾闯天下 tag unless the user or agent removes it. Also confirm any localhost rendering service is one you intentionally run.
SKILL.md:18Mandatory Branded Hashtag Injection into Generated Content
The skill is entirely specified in Chinese and includes prescriptive style requirements such as using '兄弟们', emoji, and other Chinese-platform-native phrasing for generated copy. This effectively forces a specific language/locale and tone without stating that the user can choose another language or opt in to Chinese output.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
curl -X POST "http://localhost:3710/api/content/render" \
-d '{"cover_word":"标签","cover_title":"标题","cover_description":"描述","cover_emoji":"🤖"}'
⚠️ 尺寸固定,不能自定义宽高比例