ClawHub
Back to skill

Security audit

Sensitivity Charts

Security checks for vulnerabilities and agentic risk

Overview

This is a simple sensitivity-analysis formatting skill with no code execution or data-access behavior, though its activation triggers are somewhat broad.

Install this if you want structured sensitivity-analysis outputs. Be aware it may activate for general what-if or variable-impact wording, so check that it is being used only when that analysis is intended and validate any financial assumptions yourself.

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 trigger list contains broad terms like "sensitivity," "what-if," and especially "variable impact," which can plausibly match many ordinary analytical requests outside the intended narrow skill scope. Overly broad activation can cause the skill to be invoked unexpectedly, creating prompt-routing confusion and increasing the chance that irrelevant or misleading structured outputs are injected into unrelated conversations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.