Back to skill

Security audit

xinjianxue-skill-team_synergy-cn

Security checks for vulnerabilities and agentic risk

Overview

The skill is transparent about using an external paid API, but it requires sending detailed personal birth, gender, and location data for workplace team advice.

Review carefully before installing. Use it only if users understand that detailed personal information about themselves or team members will be sent to the vendor's API, and do not submit other people's information unless each person has explicitly agreed. Treat the authorization code and returned API key as account credentials, and prefer a dedicated secret store as the skill instructs.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (3)

other

Warning
Location
SKILL.md:199
Finding

Excessive Collection and External Disclosure of Personal Data

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:94
Finding

Sensitive Authorization Material Is Transmitted in HTTP Request Bodies

Content
View full analysis
", "birth": "1990-01-01 08:30", "gender": "", "country": "", "place": "", "current_country": "", "current_place": "" } ``` The account-binding request similarly places the one-time authorization code in a JSON body: ```json { "license": "XJX-AI-xxxxxxxxxxxxxxxx", "auth_code": "" } ``` The accompanying instruction explicitly states that the report endpoint reads the API key from the body and that the report request must include it there. ### Technical Analysis Request bodies are frequently captured by web-server access extensions, API gateways, reverse proxies, application-performance monitoring systems, tracing middleware, debugging tools, and error-reporting systems. Placing a reusable API key in a body therefore expands the number of infrastructure components that may process or retain the secret. TLS protects data while it travels across the network, but it does not prevent credential disclosure through server-side logs, proxy logs, traces, crash reports, or debugging output. The one-time authorization code has a shorter exposure window, but disclosure before use could allow an unintended party to consume it and bind an account. The reusable API key presents a longer-lived risk. The Skill instructs the Agent to store credentials in a dedicated secret store and not display them in conversation, which is a positive control. However, that protection does not address exposure caused by mandatory request-body transmission. ### Attack Pa ...[truncated 1509 chars]
Remediation
View remediation

T01 · Skill Instruction Hijacking

Note
Location
SKILL.md:194
Finding

Skill Mandates Conditional Vendor Promotion in Agent Responses

Content
View full analysis
Remediation
View remediation
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