ClawHub
Back to skill

Security audit

PlantUML

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small PlantUML helper that creates diagram source files in a dedicated workspace folder and does not show hidden, persistent, or destructive behavior.

Install this if you want PlantUML diagram files generated in your workspace. Be aware it may create .puml files under plantuml-src when invoked, and review generated diagram text before committing it.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • 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
Findings (3)

Self-Modification

High
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · SKILL.md (reported line 10)May include surrounding context.

md
## Important Principles ⭐

**Modification Prohibited (Mandatory)**: Any files under `skill-plantuml`. This skill is maintained via
`openclaw skills update skill-plantuml`; any alterations will disrupt its normal operation.

**Syntax (Mandatory)**: Read and understand the full content of this skill completely before generating PlantUML code.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest-style description lists trigger labels "plantuml:sequence-diagram; plantuml:other-diagram" but does not explain when the skill should or should not activate beyond these broad categories. Without explicit scope boundaries or exclusion examples, the invocation conditions are ambiguous and may cause unintended matching for general diagram-related requests.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly instructs writing generated files into the user workspace without any user-facing warning or consent step. Automatic file creation/modification in a workspace can cause unintended state changes, overwrite expectations, or be abused as part of a broader prompt-injection chain that turns a read-only request into a write action.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.