ClawHub
Back to skill

Security audit

Seqera

Security checks across malware telemetry and agentic risk

Overview

This skill is mostly a normal Seqera connector, but it presents itself as read-only while also enabling workflow launches and includes remote installer commands users should review carefully.

Install only if you trust OOMOL and intend to operate Seqera through its `oo` CLI. Treat `launch_workflow` as a write action even though it is not labeled that way here, and confirm the exact payload, workspace, pipeline, and cost impact before running it. Review the CLI installer source or use OOMOL's documented installation path instead of blindly running pipe-to-shell commands.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Description-Behavior Mismatch

High
Confidence
96% confidence
Finding
The manifest and description claim the skill is for 'searching and reading data,' but the documented actions include `launch_workflow`, which changes Seqera state. This mismatch can cause a caller or higher-level agent to treat the skill as read-only and invoke it in situations where state-changing operations were not expected, increasing the risk of unintended workflow launches.

Vague Triggers

Medium
Confidence
85% confidence
Finding
The trigger phrase says to use this skill for 'ANY Seqera request,' which is overly broad and encourages routing all Seqera-related tasks through a single capability without clear scope boundaries. In context, that broad routing is more dangerous because the skill includes both read and write operations, so benign discovery tasks and state-changing tasks are funneled through the same entry point.

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
98% confidence
Finding
The skill instructs users to execute `curl -fsSL https://cli.oomol.com/install.sh | bash`, which downloads and immediately executes a remote script without verification. If the remote host, TLS path, or served script is compromised, this becomes arbitrary code execution on the user's machine; embedding it in a skill increases the chance an agent or user treats it as trusted setup guidance.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.