ClawHub
Back to skill

Security audit

Scamper

Security checks for vulnerabilities and agentic risk

Overview

This is a simple brainstorming-method skill with transparent, low-impact behavior and no executable code.

Install this if you want a SCAMPER brainstorming helper. Be aware it may appear during general idea-development requests, and review any suggested append to notes/ideas.md before accepting it.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The activation criteria are broad enough to trigger on generic brainstorming or idea-expansion requests, not just an explicit invocation like "SCAMPER this." That can cause the skill to run when the user intended a different workflow, increasing the chance of unintended behavior, prompt-scope drift, and unnecessary exposure of user content to this skill’s instructions.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The automatic prompt to offer SCAMPER immediately after saving an idea creates a follow-up pathway that may repeatedly steer users into this skill without strong scope checks. While it still asks for consent, the pattern can encourage over-invocation and workflow creep, especially in automated note-processing contexts where many ideas are saved in sequence.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.