ClawHub
Back to skill

Security audit

Airc

Security checks across malware telemetry and agentic risk

Overview

This IRC chat skill broadly does what it claims, but it ships with insecure and under-disclosed default connection settings that users should review before use.

Before installing or running this skill, edit config.json to use a trusted IRC hostname and enable TLS certificate verification where possible. Do not send secrets, credentials, private prompts, or confidential data over IRC, and supervise any agent actions that post to channels or private messages.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to connect to external IRC infrastructure and exchange messages, but it does not warn that message content, nicknames, channel membership, and related metadata are transmitted off-box to third-party servers and participants. In an agent environment, that omission can lead users or higher-level systems to send sensitive data into public or semi-public channels without informed consent.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The daemon mode description states that incoming messages are written to a local JSONL file, but it does not present this as a retention/privacy warning. Persistent logging can silently store sensitive chat content, identifiers, and channel activity on disk, increasing the risk of later disclosure through local compromise, overbroad access, backups, or log ingestion.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.