Back to skill

Security audit

Team Manager

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Russian-language team reminder workflow with limited local status tracking and no executable code.

Install this only if a Russian-language workflow on Moscow time fits your team. Before relying on it for real team tracking, confirm where state.json is stored, what response status data it contains, and how to delete or rotate that local state.

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
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The entire skill description is presented in Russian and hard-codes Moscow time (МСК) for scheduled interactions, indicating a specific language/locale constraint. The file does not state that this skill is region-specific or offer users a language or timezone choice, which may violate language/locale policy requirements.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly states it stores user response status in a local state.json file, but provides no notice about retention, scope of stored data, or handling of that data. While not inherently malicious, undocumented persistence can create privacy and compliance issues, especially if users are unaware their activity history is being retained.

Content

No source excerpt is available for this finding.