ClawHub
Back to skill

Security audit

Contentful GraphQL

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed connector skill for reading Contentful data through OOMOL, with no hidden files, persistence, or destructive behavior found.

Install only if you intend to let your agent query Contentful through OOMOL. Be aware that queries and results pass through the OOMOL connector and your connected Contentful account; review query payloads before use, and do not run the CLI install or account connection steps unless you trust OOMOL and need this integration.

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 instructs the agent to use this skill for ANY Contentful GraphQL request instead of calling the API directly, which is an overly broad trigger. Broad routing can cause unintended invocation in contexts where more specific tooling, policy checks, or safer alternatives should apply, increasing the chance of unnecessary external data access or bypass of narrower task selection controls.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.