Back to skill

Security audit

blog generation 博客生成skill,去除AI味,更有可读性~

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese technical blog-writing skill with no hidden execution, credential access, or persistence beyond optional article files.

Install this if you specifically want help drafting Chinese technical blog posts. Review facts, code, news links, and the final save path before approving a completed article.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
93% confidence
Finding

The description and opening instructions define the skill as a Chinese technical blog writer and describe its behavior entirely as producing Chinese content. There is no indication that users can choose another language or explicitly opt into the locale constraint, which matches the language/locale policy violation category.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The document is explicitly framed as a Chinese writing style guide and presents its guidance as normative for the skill, but it does not indicate that Chinese is optional or limited to a region-specific use case. This can violate language/locale policy when a skill forces a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The file forces a single language/locale experience through its title and full body content, with no opt-in or note that the skill/article is intentionally region- or language-specific. Under the policy, natural-language content that imposes a specific language without user choice can be a locale-policy issue.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The article’s illustrative workflow has the agent look up a contact and send an email on the user's behalf, which is a privacy- and action-affecting behavior. In this markdown file, there is no accompanying warning or disclosure that such actions can transmit user data externally or should require explicit user awareness/confirmation.

Content

No source excerpt is available for this finding.