Security audit
ap-invoice-processing
Security checks for vulnerabilities and agentic risk
Overview
This skill automates invoice intake with clearly disclosed email, spreadsheet, and AP-system actions while keeping approval and payment under human control.
Before installing, confirm the exact inbox or label, AP-log columns, forwarding destination, exclude patterns, and lookback window. Use a limited mailbox or label if possible, review the run log during initial use, and verify that forwarded invoices still require human approval before any payment is made.
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