Back to skill

Security audit

LAC CreativeRules

Security checks for vulnerabilities and agentic risk

Overview

This is a LAC POWER brand design guideline skill with no executable behavior; the main caveat is that broad trigger terms may apply its brand rules to unrelated design prompts.

Install this for LAC POWER-specific marketing and brand-compliance guidance. Users should confirm they actually want LAC POWER rules applied, adapt language for the target audience when needed, and provide authorized logo/product assets before producing final materials.

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
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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger keywords are generic design and compliance phrases such as 'brand guidelines', 'logo usage', and 'platform specs', which can cause the skill to activate for unrelated design requests. Over-broad activation can route ordinary user prompts into this brand-specific rule set, leading to inappropriate constraint injection, unintended policy shaping, and confusion or misuse of brand assets outside the intended context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

This markdown guide is primarily written in Chinese, but it prescribes an English slogan and English-centric typography as default brand content without indicating whether language selection depends on audience or user preference. That can be a locale/language policy concern because it hard-codes one language presentation rather than offering an explicit opt-in or audience-based choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

Most of the skill instructions and constraints are presented only in Chinese, which can functionally impose a language preference on users. The file does not state that the skill is China-specific, nor does it offer an opt-in or alternative language behavior for users who may need English output.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

This markdown file is primarily written in Chinese, but line L008 hard-codes the slogan in English. Because the document does not state that English is optional, required for branding, or selectable by the user, it can be interpreted as enforcing a specific language without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

Lines L108 and L115 provide English-only example marketing text in an otherwise Chinese design guide. Without an explicit note that these are optional examples, bilingual defaults, or required brand assets, the file may violate language/locale policy by implicitly forcing English output.

Content

No source excerpt is available for this finding.