ClawHub
Back to skill

Security audit

Daffy

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Daffy read/search connector skill, with no artifact evidence of hidden execution, persistence, destructive behavior, or token theft.

Install this only if you are comfortable letting the skill read Daffy account information through your OOMOL-connected Daffy account. Treat the broad 'any Daffy request' wording as applying to Daffy read/search tasks, and review any future version carefully if it adds write or destructive actions.

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
92% confidence
Finding
The manifest description says to use this skill for "ANY Daffy request" and instead of calling the API directly, which is an overly broad routing trigger. Broad invocation language can cause the agent to select this skill in contexts it did not specifically validate, increasing the chance of unintended access to account-scoped financial or donation data through the connected Daffy account.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.