ClawHub
Back to skill

Security audit

Kano Model Strategist

Security checks for vulnerabilities and agentic risk

Overview

This is a product-planning guidance skill that gives strong feature-pruning advice but does not run code, access credentials, persist data, or perform hidden actions.

Install this if you want opinionated Kano-based backlog pruning. Be aware it is intentionally biased toward cutting features and may be too forceful for general project management or non-feature design discussions.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The README defines activation triggers including phrases like "cut features," "is this a must-have," and "start with NO," which are generic enough to appear in normal product conversations outside an intentional skill invocation. Although the file provides some "When NOT to use" context, it does not clearly constrain how triggers are matched or provide negative examples to prevent accidental activation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list contains broad, common phrases such as "should we build this" and generic backlog/scoping language that could cause the skill to activate outside narrowly intended Kano-analysis contexts. Unintended invocation can override a more appropriate skill or steer product decisions using this skill’s strong default stance (e.g., "start with NO"), creating reliability and workflow integrity issues even though it is not directly a code-execution or data-exfiltration risk.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The frontmatter load trigger uses broad natural-language conditions ('on demand' plus several common audit/pruning scenarios), which can cause the skill to be invoked in more contexts than strictly necessary. Over-broad activation increases the chance that sensitive or unrelated conversations pull this guidance unexpectedly, expanding the skill’s operational surface and potentially interfering with safer, more specific skills or workflows.

Content

No source excerpt is available for this finding.