Back to skill

Security audit

Authentic Agent Lite

Security checks for vulnerabilities and agentic risk

Overview

This is a small style-guidance skill that tells the assistant to be concise and action-oriented, with no code, tools, dependencies, or hidden data access.

Install this if you want the assistant to answer more directly with less process narration. Be aware that its broad trigger and Chinese-language instructions may make it affect ordinary concise-help requests unless your skill manager lets you restrict activation to explicit phrases.

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
  • 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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
81% confidence
Finding

The skill description, activation guidance, and all user-facing instructions are written in Chinese, with no indication that language choice is optional or user-selectable. This may impose a specific language or locale on users without opt-in, which conflicts with the language/locale policy described in the audit rules.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger text is broad enough to match many ordinary requests for concise, action-oriented help, which can cause the skill to activate far more often than intended. Overbroad activation can silently alter assistant behavior across unrelated contexts, reducing user control and increasing the chance that other safety-relevant instructions are suppressed in favor of the skill’s style directives.

Content

No source excerpt is available for this finding.