Security audit
tulimoa
Security checks for vulnerabilities and agentic risk
Overview
The skill provides a clearly disclosed connection to Tulimoa for finding tools and managing the user's own directory listings.
Both artifact files were inspected, and the complete scanner reports contained no findings. Searches contact Tulimoa; publishing requires account authorization. Review listing content before submitting or editing because edits to live listings appear immediately. The optional launch package costs $5 and requires your consent and checkout. Remote service behavior was not independently audited.
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
