ClawHub
Back to skill

Security audit

Shotstack

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Shotstack connector skill that can submit renders only after user confirmation, with no hidden or unrelated behavior found.

Install only if you intend to let Codex use your OOMOL-connected Shotstack account. Review render_edit payloads before approval because submitted renders may affect your Shotstack account or billing, and only run the one-time oo CLI/auth setup if you trust OOMOL.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The manifest description says to use this skill for 'ANY Shotstack request' and 'whenever a task involves Shotstack, use this skill instead of calling the API directly,' which is an overly broad trigger that can cause the agent to invoke the skill in situations where narrower review or safer alternatives would be more appropriate. Because the skill includes a state-changing `render_edit` action, broad auto-selection increases the chance of unintended writes or over-delegation without sufficient user confirmation.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.