Tp2
- Category
- MCP Tool Poisoning
- Confidence
- 85% confidence
- Finding
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
- Content
Security audit
Security checks for vulnerabilities and agentic risk
This is a coherent HeyGen video-generation skill, but users should be aware it uses local API credentials and sends scripts to HeyGen, which may incur costs.
Install only if you intend to use HeyGen from OpenClaw. Review prompts before generation because the script text is sent to HeyGen and API calls may be billed. Keep the local heygen_creds.json file protected and avoid including secrets, regulated data, or confidential material in generated scripts unless that use is approved.
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
The trigger phrases are broad enough to match common requests about video creation, which can cause the skill to activate unexpectedly. In a skill that reads local credentials and sends user content to an external API, over-broad activation increases the chance of unintended third-party data transmission and unintended billing activity.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
AVATAR_ID = creds['avatar_id']
API_KEY = creds['api_key']
BASE_URL = 'https://api.heygen.com/v1'
HEADERS = {
'Authorization': f'Bearer {API_KEY}',
The examples accept arbitrary script text and submit it to HeyGen's external API, but the skill description does not clearly disclose this data flow. Users may provide sensitive or proprietary content believing it stays local, leading to privacy, confidentiality, and compliance risks.
This code sends user-provided script content along with authentication credentials to an external HeyGen endpoint. External transmission is expected for the feature, but it is still security-relevant because sensitive user content may be exfiltrated to a third party and API usage may incur costs if triggered unintentionally.
if voice_id:
payload['video']['script']['voice_id'] = voice_id
response = requests.post(url, headers=HEADERS, json=payload)
return response.json()
# 使用示例
The natural-language instructions, examples, and labels are entirely Chinese, and there is no indication that the user can opt into another language or that the skill is intentionally region-specific. This can violate language or locale policy where skills should not force a single language without user choice or justification.