Back to skill

Security audit

Yq Gif Sticker Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently generates Chinese-caption GIF stickers from a user-provided image and publishes an online preview, with privacy considerations users should understand.

Install this if you want a Chinese-caption animated sticker workflow and are comfortable uploading the source image for AI processing and publishing the generated GIF preview online. Avoid using private faces, sensitive documents, confidential logos, or proprietary images unless you are comfortable with the transformed output being accessible through the preview link.

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
  • 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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The description mandates Chinese captions as part of the generated stickers, and the rest of the document reinforces fixed Chinese text outputs. This imposes a specific language/locale without documenting user choice or a justified region-specific constraint.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill instructs users to upload photos and sends them through image analysis and generation tools, but it does not warn users that their images may be processed by external services. This creates a privacy and informed-consent risk, especially because uploaded photos may contain faces, pets, personal objects, or proprietary logos.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The workflow deploys generated GIFs and an HTML gallery for online preview, but the skill does not clearly tell users that their transformed content may become accessible via a hosted link. If the source photo contains a person's likeness, private items, or sensitive branding, publishing derived media without explicit warning can expose user data beyond the local session.

Content

No source excerpt is available for this finding.