Back to skill

Security audit

guanguan-10agents

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed HR advice skill with no code execution, persistence, credential access, or hidden data handling, though its activation wording is broader than necessary.

Before installing, understand that this skill may activate for broad people-management language and answer in a branded HR-advisor style. It does not appear to run code or access data, but users who want tighter routing should narrow the trigger to explicit HR, employment, recruiting, compensation, performance, or labor-relations requests.

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
Findings (1)

T01 · Skill Instruction Hijacking

Warning
Location
SKILL.md:3
Finding

Overbroad Automatic Activation and Forced Persona Injection

Content
View full analysis
"老板好,我是管管,您的组织人事官。招人难、留人难、管人难?把您的团队问题告诉我,我来帮您破局。" ``` ### Technical Analysis The skill metadata directs the agent to invoke the skill whenever a request concerns broadly defined management of people. This trigger encompasses generic terms such as teams, employees, talent, and performance, rather than limiting activation to an explicit request for human-resources assistance. After activation, the skill instructs the agent to assume a named persona and supplies branded output formatting and a fixed introduction. These instructions can supersede the agent's normal presentation and distort responses to requests that merely contain one of the broad trigger concepts. The behavior therefore represents instruction hijacking at the skill-text level. The issue does not provide operating-system access, elevated privileges, code execution, credential access, or persistence. Its scope is limited to control over the agent's active-session persona, response framing, and output content. ### Attack Path 1. A user submits a request containing a broad trigger concept such as “team,” “employee,” or “performance.” 2. The metadata interprets the request as requiring immediate skill activation, even if HR assistance was not the user ...[truncated 1039 chars]
Remediation
View remediation
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 (1)

Vague Triggers

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The activation rule is excessively broad: it says HR skill must be invoked for essentially any issue involving 'people' and includes many common terms. This can cause inappropriate routing of unrelated conversations into an HR persona, increasing the chance of irrelevant guidance, privacy overreach, and bypass of more suitable domain-specific or general handling.

Content

No source excerpt is available for this finding.