Security audit
Oraclaw Calibrate
Security checks for vulnerabilities and agentic risk
Overview
This is a simple forecasting calibration skill that asks for an API key and paid scoring calls, with no hidden scripts or persistence in the submitted artifact.
Before installing, confirm you trust OraClaw with the forecasts, outcomes, source names, and probabilities you submit, and review the $0.02 USDC per-call pricing and free-tier terms. The artifact itself is Markdown-only and does not include executable code.
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