tencent-mps
What this skill does
Media processing using Tencent Cloud MPS (Media Processing Service), including video/audio/image processing, AI generation, and media quality checks.
github/leoyeai - Data Exfiltration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=tencent-mpsAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
scripts/load_env.py
The script scans multiple system files (e.g., /etc/environment, ~/.bashrc) and loads environment variables into the process. This could potentially expose sensitive information (like TENCENTCLOUD_SECRInsecure Configuration
Insecure Configuration via local-llm-review
scripts/mps_cos_upload.py
The script relies on environment variables for sensitive information (TENCENTCLOUD_SECRET_ID, TENCENTCLOUD_SECRET_KEY, TENCENTCLOUD_COS_BUCKET, TENCENTCLOUD_COS_REGION). If these variables are not proBadge
Add the Anomity scan badge for tencent-mps to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of tencent-mps? Report an issue or request a rescan.
