Security audit
alter
Security checks for vulnerabilities and agentic risk
Overview
This skill is transparent about building a local digital persona, but it asks users to ingest highly sensitive personal data while depending on missing, uninspectable companion services.
Review before installing. The visible skill text is not overtly malicious, but its intended use involves collecting and persistently indexing very sensitive personal material, including voice, documents, emails, and AI chat exports. Do not rely on its privacy, deletion, or local-only claims unless you can inspect the missing installer and Alter service implementation or obtain them from a trusted source.
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.