Security audit

Bezos Long Term Principle

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only strategy-advice skill with clear limits and no evidence of hidden execution, persistence, credential use, or data exfiltration.

Before using it, treat outputs as strategic brainstorming rather than professional financial, legal, HR, or compliance advice. Avoid sharing raw confidential business data, customer identifiers, account details, credentials, or unpublished financials unless they are first minimized or anonymized.

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

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: Line L016 states '中文为主，英文关键术语保留', which imposes a language preference in the skill description. Under the policy, forcing a specific language without user choice or opt-in is a natural-language locale violation unless clearly justified as region-specific.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.