Security audit
Security News
Security checks for vulnerabilities and agentic risk
Overview
This skill only provides commands for reading public cybersecurity vulnerability feeds through a disclosed web API.
Installers should be aware that vulnerability lookups are sent to feed-monitor.security-feeds.workers.dev, not directly to NVD or CISA. It appears suitable for public security briefings, but critical vulnerability decisions should still be verified against primary vendor, NVD, or CISA advisories.
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