ClawHub
Back to skill

Security audit

Woodpecker.co

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed read-only Woodpecker.co connector skill; the main caveats are broad routing wording and normal OOMOL `oo` CLI side effects.

Install only if you want an agent to read data from your connected Woodpecker.co account through OOMOL. Keep use to explicit Woodpecker.co read requests and the listed actions; do not use broader `oo` subcommands such as proxy, skill installation, or account-management actions unless you separately intend that.

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
87% confidence
Finding
The skill description says to use this skill for ANY Woodpecker.co request, creating a very broad routing trigger without clear task boundaries. While the listed actions are read-only in this version, such broad capture can cause the agent to over-select this skill for loosely related requests, reducing opportunity for tighter validation or safer alternative handling if the skill later expands or is misapplied.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.