Back to skill

Security audit

Generate Immigration Law Firm Client Education Handout

Security checks for vulnerabilities and agentic risk

Overview

This skill appears intended to make immigration-law education handouts, but it asks for broad shell and file-reading access that is not needed for that purpose.

Review this skill before installing. Its core handout-generation purpose is understandable, but it should remove Bash and broad Read access or replace them with user-selected document access. Outputs should be treated as drafts for attorney review, not client-specific legal advice.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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
Findings (1)

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:11
Finding

Excessive Shell and Filesystem Permissions

Content
View full analysis
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

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill’s activation guidance is overly broad: 'Use this skill for client education work for immigration attorneys, legal ops teams.' Without tighter trigger boundaries, an agent may invoke it for legal-content tasks that drift into individualized legal guidance or client-facing advice. In the immigration-law context, that ambiguity is more dangerous because generated content may be mistaken for legal advice despite only a soft note recommending human review.

Content

No source excerpt is available for this finding.