T05 · Unauthorized Access and Privilege Escalation
Error
- Location
SKILL.md:127- Finding
Overly Broad Wildcard Permissions for Tencent Cloud Resources
- Content
View full analysis
- Remediation
View remediation
Security audit
TencentCloud Lighthouse
Security checks for vulnerabilities and agentic risk
Overview
The skill is a disclosed Tencent Cloud Lighthouse manager, but it needs Review because it recommends overly broad cloud permissions and exposes destructive or billable actions without enough safeguards.
Install only if you are comfortable giving the skill Tencent Cloud authority to create, renew, modify, and delete Lighthouse instances. Do not use the wildcard CAM policy as written; create a least-privilege sub-user, remove unused VPC permissions, scope resources where possible, and add a human confirmation step before deletion. Never paste or display config/.env contents in shared logs or chats, and prefer an isolated virtual environment with pinned dependencies.
Vulnerability Patterns
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
- 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
Findings (3)
T08 · Insecure Dependencies
Warning
- Location
SKILL.md:165- Finding
Unpinned Dependencies Installed Outside Package-Management Protections
- Content
View full analysis
- Remediation
View remediation
T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:307- Finding
Troubleshooting Command Can Print Cloud Credentials in Plaintext
- Content
View full analysis
- Remediation
View remediation
Vulnerability Patterns
- 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 Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (7)
Credential Access
High
- Category
- Privilege Escalation
- Confidence
- 60% confidence
- Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
- Content
md - ✅ 使用子用户密钥，不用主账号 - ✅ 设置最小权限 - ✅ .env 文件妥善保管 - ✅ 定期轮换密钥 (90 天) - ❌ 不要提交密钥到 Git
Credential Access
High
- Category
- Privilege Escalation
- Confidence
- 60% confidence
- Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
- Content
python - ✅ 使用子用户密钥，不用主账号 - ✅ 设置最小权限 - ✅ .env 文件妥善保管 - ✅ 定期轮换密钥 (90 天) - ❌ 不要提交密钥到 Git
Credential Access
High
- Category
- Privilege Escalation
- Confidence
- 89% confidence
- Finding
The troubleshooting step tells users to run 'cat config/.env', which can print API credentials directly to the terminal, logs, screen recordings, or shared support transcripts. Even though intended for debugging, this creates a realistic secret-exposure path during operational support or collaborative troubleshooting.
- Content
问题 1: 凭证验证失败
bash cat config/.env python3 src/verify_config.py
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The skill explicitly advertises server deletion capability but does not pair it with a clear warning that deletion can permanently destroy data and may be irreversible. In an infrastructure-management skill, omission of that warning increases the chance of accidental destructive actions by users or downstream agents.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The code exposes an irreversible instance-termination operation with no confirmation prompt, dry-run mode, safeguard flag, or explicit warning to the caller. In an agent/skill context, accidental invocation, parameter confusion, or prompt-induced misuse could permanently delete cloud resources and associated data, creating a real operational security risk.
- Content
Missing User Warnings
Low
- Category
- Not specified by scanner
- Confidence
- 83% confidence
- Finding
The setup section includes a concrete .env example containing API credential variable names and placeholder secret values, but the adjacent configuration text does not clearly emphasize secret-handling precautions at the point of use. This can normalize insecure storage or copying of sensitive credentials, especially when users follow setup snippets mechanically.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 87% confidence
- Finding
The top-level docstring presents the skill description entirely in Chinese, which effectively fixes the interaction/documentation locale without any opt-in or alternative. Under the stated policy, forcing a specific language without user choice is a natural-language policy concern.
- Content
Static analysis
No suspicious patterns detected.