ClawHub
Back to skill

Security audit

Proposal

Security checks for vulnerabilities and agentic risk

Overview

This is a proposal-writing guidance skill with no code execution, external access, persistence, or hidden behavior found.

Installers should expect this skill to shape proposal-related writing, pricing, scope, and approval-path advice. For regulated, high-value, legal, tax, financial, procurement, or contract-sensitive proposals, have a qualified reviewer check the output before using it externally.

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
93% confidence
Finding

The trigger list contains generic phrases such as 'write proposal', 'review proposal', and 'pricing and scope' that can appear in ordinary business conversations without an explicit intent to invoke this skill. Overly broad triggers can cause unintended activation, pulling the model into proposal-generation behavior in contexts where the user meant something narrower or different, which can create confusion, context leakage between tasks, or workflow misrouting.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger conditions are intentionally broad and overlap with generic writing and drafting requests, which can cause the skill to activate in situations where a more specific skill would be safer or more appropriate. This is not a direct code-execution issue, but it can lead to overreach, misrouting, or unintended handling of sensitive commercial content under an overly general proposal-writing frame.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.