Book a 30-minute demo →
Skill scan report

tencentcloud-cos-skills

View on GitHub
45 Medium This skill sends sensitive values to an external host. Automated analysis flagged 2 additional risk patterns.

What this skill does

This skill provides integration with Tencent Cloud COS (Object Storage Service) and related features like image processing, document conversion, and video processing. It is designed for use with Clawd

github/leoyeai - Data Exfiltration - 2.1k stars

ThreatsData Exfiltration Configuration Misuse Privilege Escalation

Threat analysis

Data Exfiltration1 finding
Configuration Misuse1 finding
Privilege Escalation1 finding

Skill info

Nameleoyeai/tencentcloud-cos-skills
Registrygithub
Versione5199b5
PURLpkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=tencentcloud-cos-skills
Stars2.1k

Assessments (3)

Data Exfiltration1 finding HIGH
HIGH

Data Exfiltration via local-llm-review

scripts/cos_wrapper.py

The code appears to use Tencent Cloud COS for file uploads, which could potentially exfiltrate data to Tencent Cloud if misconfigured or used with malicious credentials.
Configuration Misuse1 finding MEDIUM
MEDIUM

Configuration Misuse via local-llm-review

scripts/setup.sh

The script allows for the persistence of credentials to disk with 600 permissions, which could be a risk if the system is compromised.
Privilege Escalation1 finding MEDIUM
MEDIUM

Privilege Escalation via local-llm-review

scripts/setup.sh

The script allows for the persistence of credentials to disk with 600 permissions, which could be a risk if the system is compromised.

Badge

Add the Anomity scan badge for tencentcloud-cos-skills to your README.

Anomity Skill Check badge

Markdown
[![Anomity Skill Check](https://anomity.ai/skills/badge.svg)](https://anomity.ai/skills/github/leoyeai/tencentcloud-cos-skills/)
HTML
<a href="https://anomity.ai/skills/github/leoyeai/tencentcloud-cos-skills/"><img src="https://anomity.ai/skills/badge.svg" alt="Anomity Skill Check"></a>
Image URL
https://anomity.ai/skills/badge.svg

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 tencentcloud-cos-skills? Report an issue or request a rescan.

Ask AI about Anomity
ChatGPT Claude Perplexity Google AI Grok