ClawHub
Back to skill

Security audit

Taste Vasari

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only writing-style skill with no executable behavior, though users should not rely on its outputs as factual biography without verification.

Install only if you want a stylized Renaissance biographical voice. For real art history, biographies, citations, or claims about real people and works, ask the agent to label uncertainty and verify facts rather than follow the skill's storytelling-first instruction literally.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly instructs the model to invent plausible details when facts are unknown, which encourages fabrication without disclosure. In a biographical/art-historical context, users may reasonably treat outputs as factual, so this can produce convincing misinformation and falsely attributed claims about real people or works.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.