T09 · Insecure Skill Coding Practices
Warning
- Location
src/modules/uuidGenerator.js:2- Finding
Predictable and Non-Standard UUID Generation
- Content
View full analysis
- Remediation
View remediation
Security audit
Universal Utility Toolkit - 全能实用工具包
Security checks for vulnerabilities and agentic risk
Overview
This is a coherent local utility toolkit with no hidden access or persistence, but its broad routing text and security-sensitive generators should be treated with caution.
Install only if you want a simple local utility toolkit. Do not rely on its UUIDs or passwords for security-critical systems without improving the generators, and do not expect live exchange rates despite the documentation wording.
Vulnerability Patterns
- 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
- 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 (2)
T09 · Insecure Skill Coding Practices
Note
- Location
src/modules/passwordGenerator.js:9- Finding
Biased Password Generation Through Modulo Reduction
- Content
View full analysis
- Remediation
View remediation
1024) { throw new RangeError('Password length must be an integer between 1 and 1024'); } ``` 3. If enabled options are intended as requirements, select at least one character from every enabled class. 4. Fill the remaining positions from the combined character pool. 5. Shuffle the resulting characters using a cryptographically secure Fisher-Yates shuffle based on `crypto.randomInt()`. 6. Reject lengths smaller than the number of required character classes. 7. Add statistical tests for selection uniformity and functional tests confirming that all requested classes appear. 8. Document whether each option means that a class is merely allowed or strictly required. ]]>
Vulnerability Patterns
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- 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 (5)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The manifest description says to invoke the skill for 'utility tools, converters, generators, formatters, or any common development utilities,' which is extremely broad and can cause the orchestrator to route many unrelated or sensitive requests to this skill. Over-broad routing increases the chance of unintended handling of user data and tool misuse, especially because the skill advertises many disparate capabilities under a generic umbrella.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The package description and keyword set are extremely broad and cover many generic developer tasks, which can cause the skill to be activated in contexts beyond its narrowly intended use. In agent ecosystems, overly broad activation metadata can lead to unnecessary invocation, expanded prompt exposure, and accidental handling of unrelated user requests, increasing the attack surface even without malicious code.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 82% confidence
- Finding
This markdown file uses Chinese throughout for headings and instructions, which may impose a specific language on users without any opt-in or explanation. Under the stated policy, forcing a specific language without user choice can be a natural-language policy violation.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The skill documentation is written in Chinese throughout, including feature descriptions and usage headings, with no indication that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking audience. This creates a natural-language policy concern because it imposes a specific language on users without opt-in or justification.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 83% confidence
- Finding
The skill description and headings present substantial content in Chinese while also using English labels, but there is no statement that the user can choose their preferred language. This may violate language or locale policy expectations if the skill implicitly defaults to a language without opt-in.
- Content