Security audit

test

Security checks for vulnerabilities and agentic risk

Overview

This is a China-market marketing strategy skill made of Markdown guidance, with no install steps, code execution, credential handling, or persistence beyond advisory instructions.

Install this only if you want China-focused market localization and GTM advice. Treat trend, platform algorithm, legal, regulatory, and budget recommendations as advisory and verify current sources before making business decisions or spending money.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 86% confidence
Finding: The file defines the agent as a 'China Market Localization Strategist' and frames its operation entirely around Chinese platforms, Chinese terminology, and China-market assumptions. While region-specific specialization can be acceptable, the instructions do not explicitly state that this locale constraint is intentional for a China-only use case or provide a way for users to opt into or out of the locale-specific behavior.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The title explicitly frames the skill as a "China Market Localization Strategist," which imposes a specific regional and localization context. In this file, there is no accompanying language offering user choice or documenting why this locale restriction is required, so it reads as an unqualified locale constraint.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 71% confidence
Finding: The instruction that the agent "speak[s] in actionable conclusions" is fine, but the broader skill is explicitly China-focused and includes Chinese-language platform terminology throughout without stating whether the user can choose output language or locale. Because no opt-in or language-choice mechanism is documented, the file risks enforcing a locale-specific interaction style by default.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The activation guidance says only to reference the agent "by name or specialty" when its expertise is needed, without defining specific trigger phrases, scope boundaries, or exclusion conditions. Terms like "specialty" and "need its expertise" are broad enough to overlap with many ordinary discussions about China marketing, increasing the risk of unintended invocation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The instruction "Speak the language: Use Chinese marketing terminology naturally" imposes a specific language/locale style on outputs. This is a natural-language policy concern because the file does not indicate user choice, opt-in, or a clearly justified locale constraint despite requiring a specific linguistic mode.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.