Security audit
Jinritoutiao Keyword Collector
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed browser-automation helper for collecting public Jinri Toutiao search suggestions, with no bundled executable code or hidden persistence.
Before installing, consider that it will automate a browser session against Toutiao and may use an existing browser profile. Use it with non-sensitive sessions when possible, avoid excessive automated requests, and verify that this activity complies with the site's terms and your account expectations.
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
Static analysis
No suspicious patterns detected.