Security audit
ad-spend-performance-report
Security checks for vulnerabilities and agentic risk
Overview
The bundled skill performs limited local file operations, but its reporting script does not calculate the advertised metrics and can produce misleading zeros.
Do not rely on generated reports for finance decisions until CSV parsing, calculations, missing-value handling, and attribution labels are corrected. Use a dedicated output directory because calculation.md is overwritten. The optional Windows executable is unnecessary for the local workflow and needs separate verification; the [publisher repository](https://github.com/rapidworker1/Multiple-AI-models-Toolkit) describes a general AI toolkit.
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
Static analysis
No suspicious patterns detected.