Back to skill

Security audit

privet-bogdan

Security checks for vulnerabilities and agentic risk

Overview

This skill only makes the agent print a fixed Russian greeting for Bogdan and does not request tools, files, network access, or persistence.

Install only if you want a very narrow demo skill that responds with the exact Russian phrase for Bogdan; it is intentionally not a general translation or greeting assistant.

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 (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The instruction explicitly says not to translate the phrase into other languages even if the user writes in a different language. This imposes a fixed language behavior without offering the user a language choice or documenting a justified locale-specific constraint.

Content

No source excerpt is available for this finding.