ClawHub
Back to skill

Security audit

pmo-talk-skills

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only workplace communication skill with some broad activation wording, but no hidden execution, persistence, credential access, or data exfiltration behavior.

Before installing, be aware that the trigger phrases are broad, so the skill may activate for general workplace reply requests. Review generated messages carefully for tone and facts before sending, especially in sensitive workplace disputes.

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 (3)

Vague Triggers

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger list is extremely broad and includes common phrases like '怎么回复', '帮我回', and generic persuasion requests, plus an instruction to invoke the skill even when the user did not explicitly ask for a framework. This can cause the skill to activate on ordinary communication tasks and override more appropriate behavior, leading to unsolicited manipulative or confrontational outputs in benign contexts.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger list includes very broad, everyday phrases such as '帮我回' and general persuasion/pushback language, which can cause the skill to activate in contexts where the user did not intend to use this specialized behavior. Unintended invocation is risky here because the skill steers the assistant toward generating forceful rebuttal scripts in potentially sensitive workplace interactions, which can alter tone, increase conflict, or mishandle context-specific communications.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill metadata and instructions are written to operate in Chinese and prescribe Chinese trigger phrases and output style without stating that the assistant should honor the user's current language preference. This can produce responses in an unintended locale, degrade usability, and increase the chance of miscommunication in sensitive workplace conversations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.