T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:22- Finding
WebDAV Password Exposed Through Command-Line Arguments
- Content
View full analysis
- Remediation
View remediation
Security audit
Joplin
Security checks for vulnerabilities and agentic risk
Overview
The skill is a coherent Joplin CLI helper, but it documents credential entry and destructive note deletion without enough safety guidance.
Review this skill before installing if your Joplin notes contain sensitive data. Only allow it to change sync settings or delete notes after explicit confirmation, prefer note IDs after listing targets, and avoid entering real WebDAV passwords directly in commands that may be saved in shell history or logs.
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
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
The skill description is broadly scoped ('Use for reading, creating, editing notes and managing todos') without clear activation constraints, confirmation requirements, or limits on when destructive or sensitive actions should be taken. In an agent setting, vague activation language can cause overuse of the skill in contexts involving private notes or unintended state changes.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The WebDAV setup instructions include direct credential entry on the command line without any privacy or secret-handling warning. In agent or logged shell environments, this can expose usernames and passwords through shell history, transcripts, process inspection, or accidental reuse in unsafe contexts.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The documented deletion commands allow permanent note or notebook removal but provide no warning, confirmation guidance, or recommendation to verify targets first. In an agent workflow, this increases the chance of accidental destructive actions, especially when titles are ambiguous or the wrong item is selected.
- Content
Static analysis
No suspicious patterns detected.