Security audit
portal-news-triage
Security checks for vulnerabilities and agentic risk
Overview
This skill gives scoped instructions for using a read-only news portal MCP service and does not contain code, hidden behavior, credential use, or destructive actions.
Before installing, confirm you are comfortable using the Chinng AI-Agent Portal MCP endpoint for news searches. Treat portal results as a research aid, retain original source links, and remember that a remote MCP service can change independently of this reviewed skill.
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.