ClawHub
Back to skill

Security audit

Quiver Ai

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small documentation-only integration for QuiverAI SVG generation, with expected remote API use and no executable install or persistence behavior.

Before using the API, treat prompts, reference image URLs, and uploaded images as data sent to QuiverAI, and avoid submitting sensitive material unless that fits your privacy and account requirements.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file documents sending prompts and image URLs to a remote API using an Authorization header, which is a privacy-relevant behavior for users. The reference includes authentication and request examples but provides no user-facing warning or disclosure that request contents are sent to QuiverAI for processing.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.