ClawHub
Back to skill

Security audit

Proposal Writer

Security checks for vulnerabilities and agentic risk

Overview

This is a simple proposal-writing prompt skill with no executable code, tool access, or persistence.

Before installing, understand that the skill will shape proposal drafts with persuasive sales framing such as urgency, ROI, and tiered pricing. Review generated claims for accuracy and be aware the README advertises an external paid resource, but the skill itself does not run code or access data.

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
Confidence
95% confidence
Finding
The example trigger phrase is broad enough to match ordinary user requests like proposal-writing help, which can cause the skill to activate unintentionally in unrelated contexts. Overly broad invocation patterns increase the risk of prompt-routing mistakes, unexpected data exposure to the skill, or user confusion about why this skill was selected.

Static analysis

No suspicious patterns detected.