Back to skill

Security audit

Engineering Discipline

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed coding-guidance skill that changes assistant behavior toward planning, small edits, and verification, with no hidden code, data access, or automatic persistence.

Install this if you want broad coding-process guardrails. Be aware that it is intended to shape most coding sessions, so it may add friction by asking for clarification, limiting refactors, or insisting on verification steps.

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
95% confidence
Finding

The trigger list includes broad phrases like 'coding discipline', 'production quality', and 'AI coding rules', which are common in normal engineering discussion. In systems that invoke skills from keyword matching, these generic triggers can accidentally activate the skill in unrelated conversations, altering assistant behavior unexpectedly and increasing instruction collision risk.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The instruction to apply this skill to every coding session makes activation effectively global rather than scoped to a specific task. In agent environments that auto-load or prioritize skills based on trigger text, this can cause unintended invocation, prompt bloat, and persistent behavioral override that interferes with task-specific safeguards or user intent.

Content

No source excerpt is available for this finding.