Security audit
Android Dev Agent
Security checks for vulnerabilities and agentic risk
Overview
This is a straightforward Android development helper skill with disclosed file, shell, and reporting behavior that fits its stated purpose.
Before installing, expect this skill to run normal Android development commands, create worktrees and reports, and potentially use substantial disk, network, and CPU when syncing or building AOSP. Review requested source changes or patches before applying them, but the artifact does not show deceptive, persistent, or unrelated behavior.
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
