Back to skill

Security audit

xinjianxue-skill-bff-cn

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed remote-service integration for a relationship-advice report, but it requires sensitive account binding and personal profile data.

Install only if you are comfortable authorizing this agent to bind to your Xinjianxue account, store the resulting service credentials in a secret store, and send the listed personal details to the vendor API for each report. Treat the one-time authorization code as sensitive and provide it only when you intentionally want to bind this skill.

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 (2)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:127
Finding

Sensitive One-Time Authorization Code Collected Through the Chat Channel

Content
View full analysis
Remediation
View remediation

T01 · Skill Instruction Hijacking

Note
Location
SKILL.md:194
Finding

Mandatory Referral and Social-Promotion Messaging Injected into Error 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