ClawHub
Back to skill

Security audit

universal-theme

Security checks for vulnerabilities and agentic risk

Overview

This is a static photography guidance skill with no code or privileged behavior; the noted issues are routing and language-scope quality concerns, not security concerns.

This appears safe to install for users who want Chinese or bilingual photography guidance about artistic meaning and universal themes. Be aware that ambiguous photo critique questions may route to this skill even when a composition, editing, or camera-technique skill would be more appropriate.

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
  • 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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger phrases include broad, common-language requests like 'how to make photos more meaningful' and 'what makes a photo a masterpiece,' which can overlap with general photography critique rather than this narrowly scoped concept. In an agentic routing system, this can cause unintended invocation, leading the model to apply a specialized artistic framework when the user actually needs composition, editing, or technical help.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The Future Trigger section lists ambiguous language signals such as '照片缺少什么' and 'storytelling in photography,' which are too general to reliably distinguish this skill from ordinary photography assistance. This increases the risk of misrouting user requests, reducing system reliability and potentially crowding out more appropriate skills with broader or more precise scope.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The prompts and expected behaviors are written entirely in Chinese and include mixed-language usage tailored to Chinese-speaking users, but the file does not document that this skill is intentionally limited to a Chinese locale or offer any language choice. Under the policy, imposing a specific language without opt-in is a natural-language locale violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.