混元生视频能力
Analysis
This appears to be a straightforward Tencent Cloud Hunyuan video-generation skill, but it requires Tencent cloud credentials and may upload user-selected media to Tencent’s API.
Findings (4)
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.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
pip install tencentcloud-sdk-python
The setup instructions install an unpinned Python dependency. This is a normal dependency for the stated Tencent Cloud API purpose, but version pinning is not shown.
临时禁用SSL验证(仅用于下载) ssl_context.verify_mode = ssl.CERT_NONE
The documentation includes a troubleshooting snippet that disables TLS certificate verification for downloads, which weakens connection security if followed.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
`TENCENT_SECRET_ID` - 腾讯云SecretId `TENCENT_SECRET_KEY` - 腾讯云SecretKey
The skill requires Tencent Cloud account credentials. This is expected for the Tencent API integration, but those credentials authorize actions in the user's cloud account.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
with open(image_input, 'rb') as f:
image_base64 = base64.b64encode(f.read()).decode('utf-8')
image.Base64 = image_base64For local image inputs, the script reads the specified file and includes its base64 content in the Tencent Cloud API request.
