ClawHub
Back to skill

Security audit

Personal Statement

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple healthcare admissions personal-statement helper with no evidence of hidden access, persistence, exfiltration, or destructive behavior.

Before installing, note that the skill may be selected for some general academic writing prompts because of broad wording, but its actual artifacts are limited to personal-statement drafting and a harmless sample script. Use it for healthcare admissions writing and route unrelated academic work elsewhere.

A.I.G

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

SkillSpector

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
96% confidence
Finding

The activation guidance is broader than the skill's stated domain, especially by allowing use for generic academic writing tasks with vague criteria like 'explicit assumptions' and 'reproducible output format.' In an agentic environment, this can cause the skill to be selected for out-of-scope requests, leading to inappropriate prompt steering, lower-quality outputs, or accidental handling of tasks with different safety or privacy requirements.

Content

No source excerpt is available for this finding.