ClawHub
Back to skill

Security audit

Gitea Workflow Dispatch

Security checks across malware telemetry and agentic risk

Overview

This skill performs the disclosed task of triggering a chosen Gitea or Forgejo workflow, with expected token use and no evidence of hidden data collection or persistence.

Install only if you intend to let this skill start workflows on your Gitea or Forgejo instance. Use a dedicated least-privilege token limited to the intended repositories and actions, try dryRun when unsure, and remember that triggered workflows may run code, consume runner resources, use workflow secrets, or deploy changes depending on repository configuration.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill requires access to sensitive environment variables and executes Node/shell-capable behavior, but it does not declare explicit permissions governing those capabilities. That creates a security gap where a user or platform may not have clear visibility into what privileged actions the skill can perform, increasing the chance of unintended token use or API actions such as triggering remote workflows.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
index.js:50