ClawHub
Back to skill

Security audit

agent-bom discover aws

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AWS inventory helper that uses read-only operator credentials and local output paths, with no evidence of hidden persistence or destructive behavior.

Install only if you are comfortable letting the agent use an operator-approved, preferably read-only AWS profile to enumerate cloud resources. Confirm the profile, region, services, and output path before running, and treat generated inventory as sensitive infrastructure data.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
- python
      env: []
      credentials: aws-read-only
    credential_policy: "Use the operator's existing AWS SDK credential chain. Prefer AWS SSO, WebIdentity, or STS assumed-role credentials. Do not ask users to paste access keys. Do not print credential values."
    optional_env:
      - AWS_PROFILE
      - AWS_REGION
Confidence
80% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Static analysis

No suspicious patterns detected.