Back to skill

Security audit

Life Analyzer

Security checks for vulnerabilities and agentic risk

Overview

This is a simple text-only self-reflection skill with no code execution or data access, but it should be used carefully because it gives blunt personal analysis.

Install only if you want direct self-reflection on text you choose to share. Avoid using it as therapy, crisis support, medical advice, or a substitute for a qualified professional, and be aware that its prompts favor blunt interpretation over comfort.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill processes highly sensitive personal content and produces blunt psychological-style judgments such as blind spots, contradictions, and root issues, but the description provides no warning about this sensitivity or the non-clinical nature of the output. Users may disclose intimate information without informed consent, misinterpret the output as mental health guidance, or be harmed by harsh analysis delivered without appropriate framing.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger conditions are broad enough to activate on ordinary personal conversations, including sensitive emotional disclosures, without making clear that the user is invoking a reflective analysis skill. In the context of a skill that performs psychological-style interpretation of thoughts and journal entries, this increases the chance of unsolicited profiling-like analysis and overreach into sensitive mental health territory.

Content

No source excerpt is available for this finding.