Security audit
Experiment Designer
Security checks for vulnerabilities and agentic risk
Overview
This skill is a plain Markdown guide for designing and interpreting A/B tests, with no evidence of hidden execution, persistence, or data access.
Before installing, consider that the skill may ask for business metrics such as baselines, sample sizes, and experiment results. That is expected for A/B test analysis, but users should avoid sharing confidential data unless appropriate and should validate statistical recommendations for high-stakes decisions.
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.