Security audit

Cloud Cost Audit

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown cloud cost audit guide that asks users to provide billing or architecture details, with no code execution or hidden system access.

Before using this skill, share only the minimum billing and architecture information needed for analysis. Redact account IDs, credentials, customer data, internal hostnames, sensitive topology details, and any confidential business information unless you intentionally want the agent to process it.

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
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The usage guidance invites users to provide 'any cloud cost data' and says the agent 'handles the rest,' which is an overly broad intake pattern with no stated scope limits, exclusions, or minimization guidance. In a cloud-audit context, this can lead users to submit architecture details, billing exports, and other sensitive operational data that may exceed what is necessary, increasing the risk of inadvertent disclosure or unsafe downstream processing.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The README explicitly encourages sharing billing exports, architecture descriptions, and stack details, all of which can contain sensitive financial, security, and infrastructure information, but it provides no privacy warning or data-handling safeguards. In a cloud cost optimization skill, this context makes the issue more dangerous because those artifacts often reveal account structure, vendors, usage patterns, and internal system design that could aid reconnaissance or expose confidential business information.

Static analysis

No suspicious patterns detected.