ClawHub
Back to skill

Security audit

tradeoff-analysis

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain Markdown guide for structured tradeoff analysis and does not request unusual access or perform hidden actions.

Install this if you want agents to use a structured decision matrix for concrete choices. Be aware it may activate on casual comparison phrasing, so give explicit instructions when you only want brainstorming or a lightweight opinion.

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
91% confidence
Finding

The listed trigger examples include phrases like "compare these", "which should we pick", and "is it worth it", which are common conversational expressions and can overlap with many non-skill-specific requests. Although the document provides some scope, it does not define explicit activation boundaries or negative examples for these phrases beyond a general skip note.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.