Back to skill

Security audit

Runbooks

Security checks for vulnerabilities and agentic risk

Overview

This is a simple runbook-writing guidance skill with no code execution, data access, persistence, or hidden behavior.

Install this as a low-risk workflow aid for runbooks and operational procedures. The main caveat is that it may offer itself for some review or communication tasks that are not truly runbook-related, so accept the workflow only when that structure is useful.

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

This markdown file defines activation guidance, so vague-trigger review applies. The phrase "User mentions runbooks or closely related work" does not clearly bound what counts as related, which could cause the skill to be offered in conversations that only loosely overlap with runbooks.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The condition "They are preparing a review, rollout, or stakeholder communication" overlaps with many common tasks that are not necessarily runbook work. Without constraints or negative examples, the skill may activate too broadly outside its intended domain.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.