Security audit
taskbullet
Security checks for vulnerabilities and agentic risk
Overview
This skill coherently connects an agent to TaskBullet for user-approved human assistant work, with clear limits around spending, account ownership, and secrets.
Before installing, understand that this can spend prepaid TaskBullet hours and send task descriptions to a third-party human assistant service. Keep API keys in Gateway environment settings only, do not include passwords or OTPs in delegated tasks, and confirm caps before any paid work is submitted.
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.