Back to skill

Security audit

Cfcrm Build

Security checks for vulnerabilities and agentic risk

Overview

This skill is a CFCRM roadmap and checklist helper with narrow, disclosed progress tracking, though users should know checklist status may be saved persistently.

Install this if you want an agent to help track the CFCRM roadmap and version checklists. Before using checklist commands, be aware that completion/status updates may be stored in ecosystem_knowledge and reused later, so avoid recording sensitive project details unless that storage is appropriate for your workspace.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
94% confidence
Finding

The activation rules are broad enough to trigger during ordinary planning or review conversations, which can cause the agent to enter this skill unexpectedly and steer the interaction toward CFCRM-specific workflows. That creates a scope-injection risk: the skill may override user intent, bias responses, or initiate reads/writes to ecosystem state when the user only asked a general question.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to persist build completion and status data to ecosystem_knowledge without clearly notifying the user or obtaining consent. Silent persistence can expose project status, operational metadata, or user-supplied updates beyond the current session, creating privacy and integrity risks if stored data is sensitive, stale, or shared across contexts.

Content

No source excerpt is available for this finding.