Security audit
Agentlens
Security checks for vulnerabilities and agentic risk
Overview
This skill is a small code-navigation guide that reads local AgentLens documentation and does not install software, persist itself, or request unusual authority.
Installers should understand that this skill will steer the agent to trust and read .agentlens files in a project before source files. That is appropriate for navigation, but those files are still project content and should be treated with the same caution as repository documentation, especially before regenerating docs or acting on warnings from memory.md.
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.