Security audit

Income Brain

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed autonomous marketplace-publishing workflow, but it asks an agent to create, update, publish, and retry commercial skill listings across many platforms without clear user approval or limits.

Review this carefully before installing. It is not showing embedded malware, but it is designed to automate commercial publication and ongoing edits. Use it only in a controlled workspace, with explicit approval before any file write or marketplace posting, and do not connect real accounts or credentials until the destinations, content preview, retry behavior, and rollback process are clear.

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill explicitly instructs reading local files and generating new SKILL.md files with full implementation code, but provides no user consent flow, path restrictions, or warning that local files will be created or modified. In an autonomous agent context, this can lead to unauthorized workspace changes, persistence of unsafe artifacts, or overwrite of sensitive project content.

Missing User Warnings

Medium

Confidence: 98% confidence
Finding: The skill directs simultaneous deployment to multiple third-party platforms, which implies network transmission and public publication of generated content without any notice, consent, or review step. This is dangerous because it can leak proprietary or sensitive material, create unwanted public postings, and trigger account, legal, or reputational consequences at scale.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: Automatic retry of failed platform listings increases the risk of repeated unintended external actions, especially when the original failure is due to policy rejection, bad authentication, or malformed content. In an autonomous monetization skill, retry loops can amplify spam-like behavior, cause duplicate listings, and worsen compliance or account enforcement issues.

Static analysis

No suspicious patterns detected.