Back to skill

Security audit

career-decision-skills

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language career decision framework that asks the agent to research public industry/company/job information and guide a structured evaluation.

Install this if you are comfortable using a Chinese-language career-analysis workflow. It may research public information about industries, companies, and roles, and you should avoid sharing confidential offer terms or internal company details unless you are comfortable having them analyzed in the session.

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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The README presents all instructions and decision criteria only in Chinese, which can impose a language-specific experience on users without opt-in. Under the policy, forcing a specific language is a natural-language policy concern unless the skill offers a choice or clearly documents a justified regional scope.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill is entirely in Chinese and does not offer a language choice, which can cause users or supervising agents to misunderstand instructions, decision criteria, or tool-use expectations. In security terms this creates an auditability and consent problem: reviewers may be unable to reliably verify behavior, and users may invoke the skill without understanding what data gathering or workflow it will perform.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.