ClawHub
Back to skill

Security audit

Phy Investor Wechat Update

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only drafting skill for investor WeChat updates, with no code execution, persistence, credential use, or hidden data access.

Use this skill when you intentionally want to draft a message to investors. Review the generated text before sending, especially revenue, runway, customer names, fundraising details, or referral asks, because those business details may be sensitive.

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
94% confidence
Finding

The trigger list includes broad phrases such as 'investor update' and '好消息分享' that can plausibly appear in ordinary user conversations outside the intended narrow workflow. In agent systems that auto-route by trigger text, this can cause unintended activation and inappropriate generation of investor-facing content, increasing the chance of misfires or disclosure of sensitive business information into the wrong template flow.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

Help-request triggers like '求助', '需要帮忙', and '遇到困难' are highly generic and can match many unrelated conversations. If the platform uses loose trigger matching, the skill may activate in contexts involving personal, medical, legal, or other sensitive requests, steering the interaction into investor-outreach drafting when that was not intended.

Content

No source excerpt is available for this finding.