T05 · Unauthorized Access and Privilege Escalation
Warning
- Location
SKILL.md:5- Finding
Unnecessary Command-Execution Permission
- Content
View full analysis
- Remediation
View remediation
Security audit
Translate Hub Free
Security checks for vulnerabilities and agentic risk
Overview
This translation skill is mostly coherent, but it asks for unrestricted command execution without a clear translation-related need.
Review before installing. The skill appears to be a normal translation prompt package, but it should not need unrestricted shell execution for ordinary text, Markdown, or code-comment translation. Prefer a version that removes exec or clearly explains exactly when commands run and requires explicit user approval.
Vulnerability Patterns
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
- 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
Findings (1)
Vulnerability Patterns
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The README explicitly states '完全中文化交互，适配中文用户工作流', which indicates the skill is designed to enforce Chinese interaction rather than offering the user a language or locale choice. Under the policy, language constraints should be optional or clearly justified; here there is no opt-in mechanism or documented necessity for restricting interaction language.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 66% confidence
- Finding
The FAQ asserts concrete product-like operational limits and direct usability claims, but the rest of the file is only Markdown instructions without any implementation details to impose segment/file quotas or file handling. This creates an intent/documentation divergence between claimed managed behavior and what the skill content actually provides.
- Content
Description-Behavior Mismatch
Low
- Category
- Not specified by scanner
- Confidence
- 78% confidence
- Finding
The file repeatedly presents the skill as a direct translation tool that works '无需任何配置' and '无需额外API Key', but the manifest also declares allowed-tools: read exec and states partial functionality requires command execution. That is a semantic mismatch in advertised operating model, even though no executable code is shown here.
- Content
Static analysis
No suspicious patterns detected.