Back to skill

Security audit

Enterprise Change Management Lead

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent change-management advisor with a local template-generating script and no evidence of hidden data access, persistence, network use, or destructive behavior.

Installers should understand that this skill can invoke Bash to run its included Python assessment helper, but the reviewed helper only prints change-management planning outputs. Avoid pasting sensitive business details unless needed for the advisory task, and override the locale/style in your prompt if Canadian English is not desired.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 trigger list is broad and generic enough that the skill could be invoked in situations where the user did not explicitly intend to call a change-management specialist. Unintended invocation can cause context leakage into the wrong workflow, produce irrelevant authoritative guidance, or increase the chance that Bash-enabled actions are exposed more often than necessary.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The output-style instructions require "Canadian English" unconditionally. This imposes a locale preference without indicating that the user can choose another language or locale, which fits the policy's language/locale violation criteria.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.