ClawHub
Back to skill

Security audit

geo-proposal

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently generates GEO sales proposals from existing audit data, with local file output and prospect-status updates that are disclosed in the workflow.

Install this if you want a skill that creates client-ready GEO proposal documents from audit data. Be aware it can save proposal files and change matching prospect records under ~/.geo-prospects, so review generated proposals and local status changes before sending them to clients.

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
95% confidence
Finding

The manifest description contains broad trigger phrases such as 'proposal', 'proposta', 'offerta', and 'preventivo', which can cause the skill to activate in contexts where the user did not intend to generate this specific proposal workflow. Because the skill is allowed to write files and update prospect records, unintended invocation can lead to unauthorized local state changes and generation of sensitive client-facing artifacts.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill workflow performs file creation in '/.geo-prospects/proposals/' and modifies '/.geo-prospects/prospects.json', but the skill description does not clearly warn that it will persist data and change prospect state. This reduces informed consent and increases the chance that a user invokes the skill expecting a read-only summarization action, resulting in unintended data modification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.