ClawHub
Back to skill

Security audit

Wiro AI Media Assets

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because it may send reference photos to an external AI service without clearly warning users about sharing, and parts of the scan were incomplete.

Consider whether you are comfortable with reference photos being processed by an external AI service. Before installing or using the skill with private or personal images, confirm what would be shared and obtain clear approval; the scan was partial, so its results do not establish that all instructions were assessed.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

The workflow sends reference photos to an external AI service without warning the user about the data disclosure.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The workflow encourages using existing project photos and logos as references for external AI processing without explicitly checking whether those assets are approved for third-party disclosure. Although it requires approval of assets, settings, and costs before generation, that approval does not explicitly cover data sharing; private product imagery or personal photos could therefore be disclosed without informed consent. The intended use of Wiro and public reference links reduces suspicion of malicious exfiltration but does not eliminate this privacy gap.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 92)May include surrounding context.

md
## Rules

- Never overwrite an existing asset without asking: write the new one next to it (`hero-v2.webp`) or ask first.
- Name files in kebab-case after what they show (`pricing-hero.webp`, not `image1.png`), and keep the sizes in the names of icon sets where the project does (`icon-192.png`).
- Keep web images small: a hero under about 300 KB, a social card under 1 MB. Prefer WebP or AVIF for photos, PNG for flat art and transparency, SVG for logos you already have as vectors.
- Keep the original model output out of the shipped folders, or delete it once the final files exist, unless the user wants it kept.