ClawHub

Aegis Audit

Security checks across malware telemetry and agentic risk

Overview

Aegis Audit appears to be a disclosed security-auditing skill; its main risk is an optional LLM mode that can send scanned code to third-party providers if the user enables it.

Install only if you are comfortable letting the skill read the code you ask it to audit. Keep LLM analysis off for private or regulated code unless you have approved the provider and data handling terms, and avoid scanning secrets or credentials.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Harmful Content Injection

Critical
Category
Prompt Injection
Content
---

## Vibe Check personas

Aegis assigns each scanned skill a persona based on deterministic analysis:

- **Cracked Dev** — Clean code, smart patterns, minimal permissions.
- **LGTM** — Permissions match the intent, scopes are sane, nothing weird.
- **Trust Me Bro** — Polished on the outside, suspicious on the inside.
- **You Sure About That?** — Messy code, missing pieces, docs that overpromise.
Confidence
95% confidence
Finding
kill a person

VirusTotal

55/55 vendors flagged this skill as clean.

View on VirusTotal