ClawHub
Back to skill

Security audit

Predict

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local forecasting template that overstates its analytical depth but does not show hidden, destructive, or data-exfiltrating behavior.

Install only if you want a local forecasting note-taking/checklist helper. Do not rely on it for actual predictive modeling or probability estimates unless the missing analytical scripts are added and reviewed.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (5)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The declared purpose says the skill performs substantive forecasting, probability evaluation, scenario generation, and risk assessment, but the file content only provides static guidance while also persisting data locally. This mismatch can mislead users and orchestrators into trusting outputs as analytically grounded when they are not, and it obscures persistent storage behavior that may affect privacy and decision-making.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill advertises local file storage and references scripts that imply file read/write behavior, but it does not declare any explicit tool scope such as permissions or allowed-tools. This creates an authorization gap: the runtime may grant broader-than-expected file capabilities, and reviewers or users cannot clearly verify what the skill is allowed to access or modify.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest says to use the skill when the user mentions "predictions, forecasts, trends, scenarios, or future outcomes," which is a very broad activation condition with no exclusions or context limits. Terms like "trends" and "scenarios" commonly appear in everyday analysis requests, so this could cause unintended invocation beyond forecasting-specific tasks.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The module docstring claims the script forecasts trends, but the code never computes or returns a forecast. While narrower than the manifest-level mismatch, this still contributes to misleading operator expectations and can cause other components to trust a non-existent analytical result.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill advertises prediction and forecasting analysis, but the implementation only prints a generic checklist and stores user-supplied metadata. This is dangerous because downstream users or agents may rely on the output as if it were an actual forecast, creating a deceptive capability mismatch that can misinform decisions about trends, outcomes, or risks.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.