ClawHub
Back to skill

Security audit

Creativity

Security checks for vulnerabilities and agentic risk

Overview

This creativity skill stores learned creative preferences, but that behavior is disclosed, purpose-aligned, and limited to local markdown files.

Install only if you are comfortable with the agent keeping local notes about your creative tastes and feedback. Avoid asking it to save sensitive personal details in preferences.md, and periodically review or clear that file if you do not want long-term personalization.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly instructs the agent to update a persistent preferences.md file after creative tasks, which implies storing user feedback-derived preference data across sessions without any notice, consent, retention policy, or scoping rules. While not overtly malicious, this creates a privacy risk because behavioral preferences can accumulate into a user profile and may be retained or reused in ways the user does not expect.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file explicitly directs the system to continually accumulate and update user preference data after every creative task, but it provides no constraints on what may be stored, no minimization guidance, and no warning against retaining sensitive personal information. In a creativity skill that adapts to user taste over time, this creates a realistic risk of collecting behavioral, emotional, or identity-linked data unnecessarily and retaining it indefinitely.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.