Security audit

Tr Tool

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple local text-translation helper, with a functionality mismatch but no evidence of hidden, persistent, privileged, or data-exfiltrating behavior.

Install only if you need basic character substitution. Do not rely on the documented delete or squeeze examples unless the implementation is updated to support them.

A.I.G

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

SkillSpector

Vulnerability Patterns

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 96% confidence
Finding: The implemented behavior only supports basic character substitution/translation from one character set to another. The declared description additionally claims deletion and squeezing of repeated characters, which are not present in the supplied code. Resource access and overall domain are consistent, but the declared functionality is broader than the actual implementation in materially relevant ways.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.