T09 · Insecure Skill Coding Practices
Note
- Location
scripts/generate.py:307- Finding
Unsanitized User Input Allows Terminal Output Injection
- Content
View full analysis
- Remediation
View remediation
Security audit
Shuangseqiu Generator
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local lottery-number generator that uses birthday and optional personal details, with no evidence of network access, persistence, credential use, or hidden behavior.
Before installing, understand that the skill asks for a birthdate and may use a name for deterministic lottery-number generation. Use only the minimum details needed, avoid entering someone else's personal information without consent, and treat the generated numbers as entertainment rather than financial advice.
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 (1)
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 (4)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill asks for birthdate and optionally name to generate personalized outputs but does not warn users that these are sensitive personal data elements or explain how they should be handled. In this context, the omission is more dangerous because the personalization feature is central to the skill, making routine collection of identifying information likely without informed consent or minimization guidance.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The trigger phrases are broad enough to activate on general requests about birthdays, luck, or metaphysics, which can cause the skill to collect or encourage disclosure of personal data in contexts where the user did not clearly ask for a lottery-number generator. In this skill’s context, that overreach increases privacy risk and misrouting risk because the skill is explicitly designed to process birthdate and optionally name, both of which are sensitive personal attributes.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
This code file includes natural-language descriptions and user-facing behavior that assume Chinese-only usage, starting with the module docstring and continuing through the CLI text. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified, which is not present here.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 81% confidence
- Finding
The natural-language interface, usage guidance, and trigger phrases are all presented in Chinese, which effectively forces a single language experience. Under the policy, language constraints should either be optional for the user or explicitly justified as region- or locale-specific.
- Content