Back to skill

Security audit

CCO / Chief Customer Officer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed customer-success advisory guide with narrow local memory and no executable or hidden high-impact behavior.

Install only if you want the agent to remember customer-success strategy details in ~/cco/memory.md and potentially engage on retention, churn, renewals, and expansion topics according to the activation preferences you approve during setup.

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 setup instructs the agent to "start naturally" whenever it infers the user needs CCO-level help, before any scoped activation preference has been established. This creates a real prompt-scope problem: the skill may activate on loosely related business conversations and influence responses without clear user intent, causing unintended persistence and overreach.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The proposed activation triggers are broad and proactive, including engaging whenever customer success topics arise and automatically jumping into renewal or expansion discussions. In a conversational agent, such wide triggers can cause unsolicited role takeover, misrouting of general business questions into this skill, and collection of customer-success context beyond what the user intended.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.