ClawHub
Back to skill

Security audit

Proposal Writer

Security checks for vulnerabilities and agentic risk

Overview

This is a simple proposal-writing skill with no executable code, persistence, credential handling, or automatic data access.

Before installing, be aware that the skill contains promotional links and install commands for related AfrexAI offerings. Use it for proposal drafting and pricing help, and review generated business terms and financial claims 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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The example phrase on this line is broad enough that it can plausibly match ordinary user requests outside a tightly scoped invocation pattern, increasing the chance the skill activates unintentionally. In an agent environment, over-broad triggers can cause misrouting of user intent, unexpected disclosure of proposal-writing behavior, or unintended use of this skill when the user meant a general drafting request.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.