Security audit

startup-risk-radar

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only startup risk assessment framework with no code execution, credential access, persistence, or hidden side effects.

This skill is reasonable to install if you want startup failure-pattern critique. Treat its statistics and named source as advisory rather than independently verified, and be aware it may activate for broad startup, product, unit-economics, or business-model discussions.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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)

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The skill description contains broad activation phrases such as general startup evaluation, product planning, business model review, and common terms like unit economics or product-market fit. This can cause the skill to trigger in many ordinary conversations, increasing the chance of inappropriate routing, irrelevant advice, or over-application of the framework where it is not warranted.

Static analysis

No suspicious patterns detected.