Back to skill

Security audit

news-writing

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language news writing and fact-checking workflow with no executable code, persistence, credential access, or hidden installation behavior.

Install this if you want a Chinese-oriented news drafting and fact-checking workflow. Before publishing generated copy, verify cited sources and legal/privacy-sensitive claims yourself; ask explicitly for another language or bilingual output if needed.

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
92% confidence
Finding

The manifest description is entirely in Chinese and the workflow sets a default output style in Chinese-context terms, while only mentioning bilingual output as an optional requirement to be confirmed. This creates a language policy issue because the skill appears to assume a specific language/locale unless the user explicitly asks otherwise.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The entire template is written in Simplified Chinese, including headings and field labels, with no indication that the user can choose another language or that the skill is intentionally limited to a Chinese-language context. This is a natural-language policy concern because it imposes a specific language by default rather than offering opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown guide presents all operational instructions in Chinese, which can impose a language requirement on users without any opt-in or explanation. Under the policy, forcing a specific language without user choice or documented justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The document switches to Chinese instructions and explicitly constrains titles to a Chinese character length, which imposes a specific language/locale requirement. The file does not offer a user choice of language or explain that the skill is intentionally limited to a Chinese-language or region-specific context.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.