Back to skill

Security audit

Executive OS

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed communications triage helper with a clear no-send boundary and no executable install or hidden persistence.

Before installing, understand that this skill is meant to read and organize potentially sensitive inbox, chat, and local-note content. It should be used only with sources you intend to expose to the agent, and you should keep the explicit approval boundary for sending messages, changing accounts, spending money, or mutating external systems.

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
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Memory Manipulation

High
Category
Memory Poisoning
Confidence
80% confidence
Finding

Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Content

Scanner excerpt · references/source-heuristics.md (reported line 19)May include surrounding context.

md
Operational messaging:
- elevate urgent real-world coordination and short clarifications that unblock motion
- downgrade duplicate chatter and messages without clear context

Community chat:
- elevate direct mentions and scoped project responsibilities

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% 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.

Content

Scanner excerpt · references/safety.md (reported line 3)May include surrounding context.

md
# Safety

Allowed without approval:
- read signals
- classify signals
- summarize signals