ClawHub
Back to skill

Security audit

Orshot Carousel Generator: TikTok carousel, Instagram carousel, LinkedIn carousel and TikTok slideshow maker from a template

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently creates social-media carousels through Orshot and requires user review before publishing, while openly using publicly accessible images.

Use images approved for third-party processing and public accessibility. Require permission before uploading private local photos, and treat rendered links as public. Review connected accounts, captions, slides, and batch costs before publishing or scheduling.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

orshot_render_template over MCP takes the same body.

bash
curl -s -X POST https://api.orshot.com/v1/studio/render \
  -H "Authorization: Bearer $ORSHOT_API_KEY" -H "Content-Type: application/json" \
  -d '{
    "templateId": 123,

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

orshot_render_template over MCP takes the same body.

bash
curl -s -X POST https://api.orshot.com/v1/studio/render \
  -H "Authorization: Bearer $ORSHOT_API_KEY" -H "Content-Type: application/json" \
  -d '{
    "templateId": 123,

User-provided photos are sent to Orshot via public URLs without a privacy warning.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The workflow permits photos from the user's own folder but requires publicly accessible image URLs, without warning against exposing private images or requiring consent before making them accessible to Orshot. If an agent satisfies that requirement by publicly hosting sensitive photos, confidentiality can be lost before the user reviews the draft; the publishing approval safeguards do not address this earlier exposure.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.