Security audit
statement-reconciliation
Security checks for vulnerabilities and agentic risk
Overview
This skill is a narrowly scoped accounting helper that checks vendor statements against AP records and drafts, but does not send, follow-up requests.
Installers should understand that this skill is meant for financial records, so it should only be used with AP logs and vendor statements the user is authorized to process. Keep the default draft-only behavior, define match tolerance before use, and review ambiguous or missing-invoice outputs before sending anything to a vendor.
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
