ClawHub
Back to skill

Security audit

Aegis Intel Stack

Security checks for vulnerabilities and agentic risk

Overview

This skill is a short local-run guide for a utility server and does not show hidden, destructive, or credential-stealing behavior.

Before installing or running it, inspect the referenced aegis-suite project and its package scripts because those files are not included in this artifact; do not put real secrets into the copied .env unless you trust the underlying project.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 22)May include surrounding context.

bash
cd aegis-suite
npm install
cp apps/utility-seller/.env.example apps/utility-seller/.env
npm run build
node apps/utility-seller/dist/dev_server.js

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 30)May include surrounding context.

Call examples

bash
curl -s localhost:8787/call/health_ping -X POST -H 'content-type: application/json' -d '{"message":"hi"}'
bash

Static analysis

No suspicious patterns detected.