Back to skill

Security audit

Seven-Step Rigor

Security checks for vulnerabilities and agentic risk

Overview

This is a process-guidance skill that tells the agent how to approach improvement work, with no evidence of hidden code, data access, persistence, or unsafe external behavior.

Install only if you want the agent to apply a strict improvement-process framework. For sensitive workflows, review any proposed deletion of tests, approvals, dependencies, or process gates before allowing changes.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description is broadly scoped to common verbs like improve, simplify, automate, harden, refactor, redesign, optimize, or rethink, which can cause it to activate in many unrelated contexts. Over-broad activation can override more specific domain skills or inject a rigid process into sensitive tasks, leading to inappropriate guidance, workflow disruption, or unsafe recommendations when context-specific constraints are required.

Content

No source excerpt is available for this finding.