T09 · Insecure Skill Coding Practices
Error
- Location
skill.md:27- Finding
Unrestricted generation and execution of SQL from user-controlled requirements
- Content
View full analysis
- Remediation
View remediation
Security audit
datasource
Security checks for vulnerabilities and agentic risk
Overview
The skill is purpose-built for NocoBase data modeling, but it gives an agent broad database-changing authority without clear confirmation or safety boundaries.
Install only if you want an agent to make real NocoBase database changes. Before allowing tool calls, require the agent to show the planned SQL and API operations, confirm the target database, reject destructive or unrelated statements, and keep backups or rollback procedures available.
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 (6)
Shadow Command Trigger
Medium
- Category
- Trigger Abuse
- Confidence
- 70% confidence
- Finding
Shadow Command Trigger: 'create table' conflicts with built-in command 'create'
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The trigger list contains very broad, common terms such as '字段', '关系', 'collection', 'data model', and 'create table', which can cause the skill to activate during ordinary schema-design or discussion requests. Because the skill is wired to powerful database-modifying tools, over-broad activation increases the chance the agent proposes or initiates destructive state changes in contexts where the user did not clearly request execution.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill explicitly instructs use of SQL and setup APIs to create tables, relations, and seed data, but it does not require an explicit warning or confirmation before modifying the database. In a tool-enabled agent, this can lead to unintended schema changes or data insertion if the skill is triggered from an ambiguous request, making the impact materially higher than a purely advisory skill.
- Content
Overly Broad Trigger
Low
- Category
- Trigger Abuse
- Confidence
- 70% confidence
- Finding
Overly Broad Trigger: '建模' is too short and may match unintended inputs
- Content
Overly Broad Trigger
Low
- Category
- Trigger Abuse
- Confidence
- 70% confidence
- Finding
Overly Broad Trigger: '字段' is too short and may match unintended inputs
- Content
Overly Broad Trigger
Low
- Category
- Trigger Abuse
- Confidence
- 70% confidence
- Finding
Overly Broad Trigger: '关系' is too short and may match unintended inputs
- Content
Static analysis
No suspicious patterns detected.