Security audit
Actual Budget
Security checks for vulnerabilities and agentic risk
Overview
This skill is a straightforward Actual Budget integration that discloses its need for financial credentials and user-controlled budget changes.
Install only if you intend the agent to access your Actual Budget data. Use a dedicated private credentials file or environment wrapper with restrictive permissions, keep it out of repositories, review mutating actions before they run, and expect budget data to be cached locally if ACTUAL_DATA_DIR or the default cache is used.
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.