ClawHub
Back to skill

Security audit

tencent-cos-ops

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to manage Tencent COS storage as advertised, but it needs review because it can immediately delete cloud objects using user-provided COS credentials without strong guardrails.

Install only if you want an agent to manage Tencent COS objects. Use a dedicated COS key restricted to the intended bucket and prefixes, avoid granting delete unless needed, double-check object keys before deletion, enable versioning or retention where possible, and choose download paths carefully to avoid overwriting important local files.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding
The skill instructs users to configure sensitive cloud credentials through environment variables, but the manifest does not declare corresponding permissions or security expectations. This creates a transparency and governance gap: an agent or runtime may access secrets unexpectedly, making credential handling harder to audit and increasing the risk of accidental exposure or misuse.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger conditions are broad and keyword-driven, including generic terms like '腾讯云', 'COS', '对象存储', and '上传文件到云存储'. Overbroad activation can cause the skill to run in unintended contexts, increasing the chance of unauthorized file operations, accidental credential use, or destructive actions being suggested or executed when the user did not specifically intend this skill.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The documentation exposes delete capability without any warning, confirmation step, or discussion of irreversibility, prefix scope, or recovery limitations. In a storage-management skill, this is dangerous because users or downstream agents may perform permanent object deletion on the wrong key or bucket, causing data loss with little friction.

Static analysis

No suspicious patterns detected.