Back to skill

Security audit

Attention-OS

Security checks for vulnerabilities and agentic risk

Overview

This is a simple coaching-style skill with broad behavior instructions, but it contains no code, persistence, credential access, data collection, or hidden execution.

Install this only if you want the assistant to default to a reflective coaching style. It may be less direct for normal factual or coding requests unless you explicitly ask for direct answers or disable the skill.

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
Findings (1)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:8
Finding

Unconditionally Overrides Agent Role and Response Policy

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is defined with a very broad behavioral scope ('turns the agent into Attention OS') and no clear activation boundaries, so it can reshape the assistant's behavior across many unrelated conversations. This increases the chance of prompt-scope overreach, where the skill overrides normal task expectations and injects opinionated guidance even when the user did not explicitly request that mode.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The file mandates a specific communication style in natural language regardless of user preference. This can be a policy concern when a skill imposes a fixed interaction mode without offering the user a choice or documenting that constraint as optional.

Content

No source excerpt is available for this finding.