Back to skill

Security audit

Tencent Cloud Deploy Web

Security checks for vulnerabilities and agentic risk

Overview

The skill is a mostly coherent Tencent Cloud operations assistant, but it gives long-lived cloud access and can run root commands or create durable SSH access on servers, so users should review it carefully before installing.

Install only if you are comfortable giving this skill a long-lived Tencent Cloud sub-account that can change DNS/CDN/server settings and run root commands on managed servers. Use the limited agent-ops policy, keep only intended servers in scope, review or approve any server command that changes data, and remove any SSH key the agent adds when it is no longer needed.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (17)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The description frames the skill as a website deployment and DNS/CDN assistant, but the content authorizes arbitrary root-level command execution on Tencent Cloud instances via TAT, including running uploaded script files. That is materially broader than the declared purpose and can be abused for full server takeover, data destruction, persistence, or lateral operational misuse under the guise of routine deployment help.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
97% confidence
Finding

Referencing the /home/ubuntu/.ssh/ path in the context of appending the agent's own key indicates persistence of privileged access on the target host. In this skill, the danger is heightened because the same document normalizes root execution on user infrastructure, so adding SSH access is not merely diagnostic but establishes an additional durable credential foothold that may evade the user's expectations.

Content

Scanner excerpt · references/routes.md (reported line 113)May include surrounding context.

md
# 2. 直接在服务器上执行命令(root 身份,不需要 SSH)
RUN --instance <id> "uname -a; df -h /; free -m"
RUN --instance <id> --file deploy.sh --timeout 900      # 较长的部署脚本,先在本地写好
#    想用 SSH 时:用 RUN 把你自己的公钥追加到 /home/ubuntu/.ssh/authorized_keys
#    不要调用 AssociateInstancesKeyPairs:它会强制关机,并让原来的密钥失效

# 3. 防火墙:官方文档说 Linux 默认放行 22/80/443,但我们遇到过 443 不通的情况,以实际查询结果为准

Credential Access

High
Category
Privilege Escalation
Confidence
97% confidence
Finding

Referencing the /home/ubuntu/.ssh/ path in the context of appending the agent's own key indicates persistence of privileged access on the target host. In this skill, the danger is heightened because the same document normalizes root execution on user infrastructure, so adding SSH access is not merely diagnostic but establishes an additional durable credential foothold that may evade the user's expectations.

Content

Scanner excerpt · references/routes.md (reported line 113)May include surrounding context.

md
# 2. 直接在服务器上执行命令(root 身份,不需要 SSH)
RUN --instance <id> "uname -a; df -h /; free -m"
RUN --instance <id> --file deploy.sh --timeout 900      # 较长的部署脚本,先在本地写好
#    想用 SSH 时:用 RUN 把你自己的公钥追加到 /home/ubuntu/.ssh/authorized_keys
#    不要调用 AssociateInstancesKeyPairs:它会强制关机,并让原来的密钥失效

# 3. 防火墙:官方文档说 Linux 默认放行 22/80/443,但我们遇到过 443 不通的情况,以实际查询结果为准

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

This script provides a generic remote command-execution primitive on cloud servers and defaults to privileged execution, which is substantially broader than the stated website/DNS/CDN assistant purpose. In an agent-skill context, such unrestricted root shell access can be abused to install malware, exfiltrate secrets, alter system state, or destroy data if the agent is prompted or manipulated into invoking it.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill explicitly instructs use of local shell, file access, network calls, environment variables, and remote administration scripts, but it does not declare any tool scope or allowed-tools boundary. That omission weakens policy enforcement and reviewability, increasing the chance the agent can invoke overly broad capabilities or use them in unintended ways.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The document is written as an instruction set entirely in Chinese and repeatedly specifies how the agent should speak to the user, but it does not offer a language choice or ask for user preference. Under the policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This JSON contains user-facing natural-language strings in Chinese, including the explanatory text and completion text, but does not indicate that the skill is China-specific or that users can opt into another language. Under the policy rule for language/locale, hard-coding a specific language without user choice or clear justification is a violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This markdown file contains user-facing operational instructions exclusively in Chinese, including required scripts for what the agent should say to users. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly justified, which is not stated here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The instructions require the deployment-completion message to use specific Chinese phrasing and direct the agent to avoid technical terms, but they do not provide any user opt-in or alternative language option. This is a natural-language locale policy concern because it forces a specific language for end-user communication.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The module docstring and all user-facing instructions are written entirely in Chinese, and the generated user card is also hard-coded in Chinese. This imposes a specific language on users without any stated opt-in or alternative, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The code executes remote shell commands immediately via TAT and returns output, but contains no built-in confirmation, warning, or policy check before running potentially destructive operations. In an autonomous or semi-autonomous assistant, this raises the risk of accidental or prompt-induced execution of harmful commands on production infrastructure.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The script's default user is root, so any command runs with maximum privileges unless the caller overrides it. This magnifies the consequences of mistakes or misuse, turning ordinary command injection, operator error, or unsafe automation into full-system compromise.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The module docstring and all user-facing setup instructions are written exclusively in Chinese, and the workflow assumes a Chinese-speaking non-technical user. The policy for natural-language violations applies to all file types, and there is no indication that the skill offers a language/locale choice or that the Chinese-only constraint is explicitly documented as a justified region-specific requirement.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The HTML sets lang="zh-CN" and the visible title/content are entirely in Simplified Chinese, which imposes a specific language/locale on users. The file does not offer an opt-in language choice or explain that the skill is intentionally limited to a China-specific audience.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This file contains natural-language instructions and records exclusively in Chinese, but does not state that the skill is Chinese-only or offer a user language choice. Under the stated policy, forcing a specific language without user opt-in can be a locale-policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The file's natural-language instructions and all described user-facing messages are written in Chinese, and the script later emits Chinese say strings to users. This creates a language/locale constraint without any opt-in or alternative, which matches the policy category for forced language usage.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file's user-facing documentation and error text are entirely in Chinese, including usage instructions and error messaging. This imposes a language choice without any opt-in or alternative, which fits the language/locale policy violation category.

Content

No source excerpt is available for this finding.