ClawHub
Back to skill

Security audit

personality-analysis-yang

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only personality-analysis skill with no code, persistence, or data access beyond text the user provides, but users should be careful about privacy and over-interpreting people from messages.

Install only if you want the agent to perform personality-style reads from user-provided text. Avoid using it to judge people in employment, admissions, legal, medical, safety, or harassment contexts, and avoid pasting private third-party conversations without consent. Treat outputs as tentative observations about language, not reliable facts about someone's character or mental state.

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 (2)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill encourages inferring personality, emotional tendencies, and behavioral patterns from messages but does not warn about privacy, consent, or the risk of deriving sensitive traits from third-party communications. Because the skill is specifically designed to profile people from chat logs, the missing safeguard materially increases the risk of non-consensual profiling, unfair characterization, and sensitive attribute inference from limited evidence.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger criteria are broad enough to activate on common requests about writing style, character, or communication patterns without clearly constraining the task. In this skill’s context, that increases the chance the agent will perform speculative profiling on third-party text or route ordinary summarization/interpretation requests into personality inference, which can produce sensitive inferences and privacy harm.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.