ClawHub
Back to skill

Security audit

Portfolio Matrix

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown-only portfolio analysis template with no code execution, network access, persistence, or credential handling.

Install this if you want Codex to use an NPV-versus-ease portfolio matrix for project prioritization. Be aware it may activate in general conversations about NPV or prioritization, so review whether that framework is appropriate for the decision at hand.

A.I.G

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

SkillSpector

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list includes broad, generic terms such as "NPV" and "prioritization" that can plausibly appear in many unrelated business conversations. This increases the chance of unintended skill invocation, causing the agent to apply this portfolio-matrix workflow when the user did not explicitly request it, which can derail responses or expose internal routing behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.