ClawHub
Back to skill

Security audit

Meeting to Action Items

Security checks for vulnerabilities and agentic risk

Overview

This skill locally turns meeting or chat notes into structured action items, with no evidence of hidden access, persistence, network use, or destructive behavior.

Before installing, be aware that this skill may turn broad meeting-summary requests into a structured project-management format and may keep English section headers for Chinese notes. Only provide meeting or chat content you intend to have parsed.

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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation description is broad enough to match ordinary requests for meeting summarization, task extraction, or note cleanup that a general assistant could handle without invoking a specialized skill. Over-broad triggers can cause unintended skill activation, leading to surprising behavior, formatting lock-in, or unnecessary processing of sensitive meeting content in contexts where the user did not explicitly request this transformation workflow.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The listed phrases include generic requests such as '总结这个会议' and 'extract tasks', which overlap heavily with normal assistant summarization and information extraction. This creates prompt-routing ambiguity: the skill may intercept routine conversations and transform them into rigid project-management output, increasing the chance of user confusion and mishandling of confidential meeting data.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The file includes Chinese content and examples, but the '新版' output format hard-codes English section headers such as 'Meeting Summary', 'Action Items', and 'Risks'. This can amount to a language policy violation because it imposes a specific output language without user opt-in or a clearly justified locale constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This code file contains natural-language instructions and output descriptions stating the tool parses text and produces structured output in Chinese, but it does not offer any language or locale opt-in. Under the policy, forcing a specific language without user choice is a natural-language policy violation unless clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The rule says that when input is Chinese, output should be fully Chinese but section titles must remain in English. This imposes a locale/language formatting constraint without user opt-in or a documented justification, which matches the language-policy concern for natural-language policy violations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.