Security audit
Tally
Security checks for vulnerabilities and agentic risk
Overview
This is a disclosed Tally API integration with meaningful account and data access, but its sensitive actions are purpose-aligned and gated by explicit user approval.
Before installing, be comfortable granting Maton-managed access to your Tally account. Approve writes, membership changes, functions, triggers, and webhooks only after checking the exact account, resource IDs, destination URL, and whether data will be forwarded continuously. Prefer OAuth over long-lived API keys and revoke unused connections or automations when finished.
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.