Security audit

China Social Media Strategy

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed China-market social media strategy skill with no executable code, persistence, credential handling, or hidden runtime behavior found.

Install this skill when you specifically want China-focused social media strategy. Treat its platform, localization, and account-readiness output as planning guidance, and verify current platform rules, verification requirements, regulated claims, advertising, data collection, and legal obligations with official sources or qualified local counsel before acting.

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
System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
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 (7)

Direct Prompt Extraction

High

Category: System Prompt Leakage
Confidence: 85% confidence
Finding: Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
Content: Scanner excerpt · SKILL.md (reported line 38)May include surrounding context.
md
- `references/output-templates.md`: Use when formatting final strategy deliverables. - `references/validation-examples.md`: Use when checking whether outputs are complete and grounded. ## Output Rules Always explain why a recommendation fits the business. Do not recommend platforms based on popularity alone.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The file instructs that localization should consider 'Chinese culture' and related platform behavior and trends, but it does not explicitly state that this skill is only for China-market content strategy or offer an opt-in for that locale. Under the policy, forcing a specific language/locale context without user choice or documented justification is a natural-language policy concern.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 82% confidence
Finding: This markdown file contains natural-language guidance that is explicitly tailored to Chinese users and the China market. Because it frames the output objective around a fixed locale without stating that this is optional, user-selected, or justified as a region-specific skill, it may violate the language/locale policy requirement.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The reference instructs preparation of a Chinese brand name, Chinese product description, and later assigns ownership for Chinese copywriting, which imposes a specific language requirement in natural-language guidance. The file does not present this as an opt-in choice or clearly document that the skill is limited to a China-specific or Chinese-language-only context.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: Line L03 states the objective is to make the company relevant and credible to Chinese users, and later sections consistently prescribe Chinese-language and China-specific content adaptation as the default. This is a natural-language locale policy constraint without any user opt-in or indication that the skill offers alternative language or regional choices.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The instruction explicitly directs recommendations toward Chinese social media platforms only. This imposes a locale-specific constraint in natural-language guidance without giving the user a choice of market/region or stating that the skill is only for China-specific use cases.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 77% confidence
Finding: The skill is explicitly scoped to China-market social media strategy and repeatedly centers Chinese platforms and localization, but it does not clearly offer the user a choice of language/locale framing or state that this region-specific constraint is optional. This can be interpreted as a locale constraint that should be more explicitly documented as region-specific and justified to avoid policy ambiguity.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.