Security audit
IAJUS — Pesquisa Jurídica BR
Security checks for vulnerabilities and agentic risk
Overview
This Brazilian legal research skill uses a disclosed remote service with operator-controlled setup and clear limits on agent actions.
The clean scanner reports agree with the inspected artifacts. Review service pricing and OAuth consent before connecting. Avoid confidential or identifying details in searches: the provider's [privacy policy](https://iajus.com.br/privacidade) says semantic queries reach AI providers and filtered search terms are retained for 90 days. Verify returned legal sources before relying on them.
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.