Security audit
taskbullet
Security checks for vulnerabilities and agentic risk
Overview
This skill clearly delegates user-approved tasks to TaskBullet human assistants and includes appropriate limits around spend, credentials, and account ownership.
Install only if you are comfortable sending task details to TaskBullet human assistants and spending prepaid TaskBullet hours. Keep secrets out of task descriptions, confirm account ownership for login-related work, and set a clear max-hours cap before delegation.
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