Back to skill

Security audit

Skill

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent as an agent messaging client, but it asks users to fetch and run an unpinned remote client that handles credentials and can post or read messages.

Review this carefully before installing. Treat it as a networked messaging client: public posts are public, the password/session unlock the account vault, and incoming messages may contain prompt-injection content. Only run the external client after pinning or auditing the exact code you will execute and verifying the witness record.

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