ClawHub
Back to skill

Security audit

Seedance

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Seedance connector with disclosed write/delete abilities and confirmation guidance, though its CLI install fallback uses a risky pipe-to-shell pattern.

Install only if you intend to manage Seedance through OOMOL. Review payloads before approving submit or delete actions, and avoid running the pipe-to-shell installer unless you trust OOMOL's distribution channel; prefer a verified or version-pinned install method if one is available.

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (2)

External Script Fetching

High
Category
Supply Chain
Content
- **`oo: command not found`** — install the oo CLI (other platforms: <https://cli.oomol.com/install-guide.md>):

  ```bash
  curl -fsSL https://cli.oomol.com/install.sh | bash    # macOS / Linux
  ```

  ```powershell
Confidence
97% confidence
Finding
The skill recommends installing the CLI via a remote script piped directly into a shell (`curl ... | bash`), which executes network-fetched code without verification. If the distribution server, transport, or script content is compromised, this can lead to arbitrary code execution on the user's machine.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The skill description instructs the agent to use this skill for ANY Seedance-related request, including reads, writes, and deletions, without narrowing scope by operation type or requiring additional routing checks. That broad trigger can cause over-invocation of a high-privilege integration and increases the chance the agent performs unintended state-changing or destructive actions through this connector.

Static analysis

No suspicious patterns detected.