Tp2
High
- Category
- MCP Tool Poisoning
- Confidence
- 85% confidence
- Finding
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
- Content
Security audit
Policy India
Security checks for vulnerabilities and agentic risk
Overview
This is a disclosed India-policy lookup skill with no executable code or hidden access, but users should verify regulatory and tax answers against official sources.
Install this if you want help researching India trade, certification, tax, or incentive policies. Because those rules can affect shipments, taxes, and compliance obligations, treat outputs as research assistance and verify important decisions against official BIS, DGFT, GST, and DPITT notices or a qualified advisor.
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
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 76% confidence
- Finding
The changelog states the skill now supports Hindi keyword recognition, but the document does not indicate whether language handling is optional or user-selected. Because locale/language behavior is mentioned without explicit opt-in or choice, this can be read as a language-policy concern under the file's natural-language instructions.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 78% confidence
- Finding
The name and description explicitly target the India market and present the skill as an India-policy query tool, but the metadata does not indicate that this locale restriction is user-selectable or opt-in. Under the policy, locale constraints should either offer user choice or be clearly documented and justified as region-specific.
- Content