Back to skill

Security audit

V.A.R. Protocol

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain-language workflow for safer versioning, backups, and rollback during editing work, with no executable code or hidden data behavior.

Install this if you want agents to be more disciplined about backups, version names, changelogs, and rollback points. Expect it to create or preserve extra local copies during larger edits; for small one-off changes, you may need to tell the agent not to apply the full protocol.

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
93% confidence
Finding

The manifest description says to use the skill for editing a very wide range of artifacts and to trigger on broad request types like refactoring, revision, redesign, rework, and collaboration. These terms overlap with common project requests and do not clearly bound when the skill should not activate, increasing the chance of accidental invocation.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The instruction to apply V.A.R. whenever overwrite cost is higher than the cost of being more disciplined is subjective and difficult to evaluate consistently. Without concrete thresholds or exclusions, different agents may invoke the skill in inconsistent situations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.