Back to skill

Security audit

Promotion

Security checks for vulnerabilities and agentic risk

Overview

This skill is a China e-commerce promotion guide that uses public shopping-platform information and avoids private account or purchase actions.

Install this if you want help interpreting public promotions on mainland China shopping platforms. It may naturally use China-market framing or Chinese-style deal phrasing, so users who need another language or non-China platforms should ask explicitly for that.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file says the skill should 'feel like a Chinese e-commerce campaign operator,' which imposes a specific language/locale style regardless of user preference. This is reinforced later by Chinese-only example phrasing, with no indication that the user can choose another language or locale.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The 'Preferred phrasing' section provides only Chinese output templates and presents them as the desired response style. Because the document does not offer opt-in or alternative-language behavior, this amounts to a locale/language policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The file’s user-facing metadata is primarily Chinese, but the default prompt is written in English and instructs the model in that language without offering a language choice. This can violate language/locale policy expectations when users are not given an explicit opt-in or selection mechanism.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The description is entirely in Chinese and explicitly limits the skill to '中国大陆平台' (mainland China platforms), which imposes a specific language/locale context without any indication of user opt-in or alternative locale support. This can violate the language/locale policy when a broader audience may invoke the skill without being offered a choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.