ClawHub
Back to skill

Security audit

geo-compare

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent GEO audit comparison skill, with a few scoping cautions but no evidence of deception or unsafe behavior.

Install only if you want an agent to work with GEO audit records under ~/.geo-prospects and generate monthly client reports. Before use, prefer providing two explicit audit files or requiring confirmation before any fresh audit is run, especially because the skill contains conflicting single-audit instructions and broad trigger phrases.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Intent-Code Divergence

Medium
Confidence
91% confidence
Finding
The skill contains conflicting instructions about whether a delta report may be produced with fewer than two existing audits. Telling the agent to use one stored file as a baseline and then run a fresh audit as the current state expands a read/compare workflow into a state-changing or externally scoped action, which can lead to misleading reports and unintended tool use.

Context-Inappropriate Capability

Medium
Confidence
88% confidence
Finding
This compare/reporting skill instructs the agent to run a fresh audit when only one file exists, which exceeds the declared purpose of comparing audits and generating a monthly report. That scope expansion can trigger unexpected networked or system actions, consume resources, and operate on a target the user did not explicitly authorize in the current request.

Vague Triggers

Medium
Confidence
79% confidence
Finding
Very broad activation phrases such as 'compare', 'delta', and 'progress' increase the chance that this skill is selected for unrelated requests. In this skill's context, accidental activation is more concerning because the workflow can escalate into reading local audit files and potentially triggering a fresh audit, amplifying the consequences of misrouting.

Static analysis

No suspicious patterns detected.