Security audit
Infinity Context
Security checks for vulnerabilities and agentic risk
Overview
This skill stores and searches agent conversation history locally, and its sensitive behavior is clearly disclosed and bounded.
Install only if you want your agent sessions kept in a local searchable archive. Treat the archive as sensitive despite best-effort redaction, keep it out of synced or shared folders, confirm first-run archiving intentionally, and use the documented off switch or cleanup tools when you no longer want history retained.
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.