Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 70% confidence
- Finding
Without declared permissions the skill's intent is opaque and cannot be validated.
- Content
Security audit
token-use-optimizer
Security checks for vulnerabilities and agentic risk
Overview
This skill is a coherent token-auditing helper that reads AI-agent project configuration files and gives optimization advice, with no evidence of hidden execution, exfiltration, or persistence.
Install this if you want Chinese-language guidance and a local script for auditing token overhead in AI-agent project files. Before acting on its optimization advice, review any proposed rule, memory, or knowledge-base deletions because those changes can alter agent behavior even though the skill itself does not make those changes automatically.
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
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- 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
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The text states that the token estimation coefficient is based on Chinese content and the entire skill guidance is written as Chinese-default operational instruction, with no indication that users may choose another language or that the scope is region-specific. This creates a natural-language locale policy concern because it implicitly standardizes a specific language without opt-in.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The entire skill reference content is written in Chinese and does not state that language selection is optional or that the document is intended only for a Chinese-speaking or region-specific audience. Under the policy, forcing a specific language without user opt-in can constitute a natural-language locale violation.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The user-facing natural-language documentation is entirely in Chinese, including the tool description, usage, and options, with no indication that another language is supported or that the user can choose their preferred locale. This can violate language/locale policy when a skill implicitly requires a specific language without opt-in.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 77% confidence
- Finding
The manifest description and main content are primarily in Chinese, while some trigger phrases are in English. Because the skill does not state that users may choose their preferred language, it may impose a language expectation on users without explicit opt-in.
- Content
Static analysis
Detected: suspicious.prompt_injection_instructions
Prompt-injection style instruction pattern detected.
Warn
- Code
- suspicious.prompt_injection_instructions
- Location
- references/optimization-strategies.md:212