ClawHub
Back to skill

Security audit

Jiminny

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Jiminny connector that reads account data through the OOMOL oo CLI, with no hidden files, persistence, or destructive behavior found.

Install only if you intend agents to access Jiminny data through your OOMOL connection. Because the skill can retrieve organizational call records and transcripts, users should ask for specific activities, date ranges, or records rather than broad searches when sensitive conversations may be present.

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
90% confidence
Finding
The description says to use this skill for "ANY Jiminny request" and to prefer it over calling the API directly, which is an overly broad invocation trigger. Broad routing language can cause the agent to invoke this skill in unintended contexts, expanding access to organizational call data and transcripts beyond the minimum necessary scope.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.