Back to skill

Security audit

Company

Security checks for vulnerabilities and agentic risk

Overview

This skill is a planning guide for designing agent-assisted company functions and does not contain executable code, hidden installation steps, or credential/data access instructions.

Before installing, treat this as a strategic planning skill: use it to map functions and define oversight, but do not allow agents to handle finance, legal, HR, customer-facing, or publishing workflows without explicit scoped tools, human approval points, rollback criteria, and audit logs.

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
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger phrases are broad business-language prompts such as 'agents for my business' and 'which skills do I need', which are likely to match ordinary conversation rather than a clear request for this specific skill. That can cause unintended activation, leading the agent to steer users into organization-automation workflows when they may have been asking a general business or strategy question.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The section 'Create a custom skill when:' gives broad conditions such as 'No existing skill covers the function' and 'Domain expertise is unique' without defining concrete trigger phrases, scope boundaries, or exclusion cases. In a markdown skill document, this can lead to inconsistent or overly broad invocation criteria for creating custom skills.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.