Back to skill

Security audit

Weekly Report Skill-周报生成

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only weekly-report formatting skill with disclosed Chinese report output and no executable behavior, persistence, or external data access.

Install this if you want manager-ready Chinese R&D weekly reports from work notes. Review source notes before use because the skill may summarize chat history or work logs you provide, and use a different tool or explicit instruction if you need another language or an unfiltered technical summary.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 75)May include surrounding context.

md
- `跨页表格解析`、`表头识别`、`单元格还原` -> `完成表格解析能力优化,提升复杂表格结构还原效果`
- `知识召回`、`RAG 检索`、`向量检索体验` -> `完成知识召回链路优化,提升检索准确性与问答支撑能力`

## Output Rules

Use Markdown only.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The activation description is broad enough to trigger on generic requests like organizing, polishing, or summarizing text, which can cause the skill to activate outside its intended weekly-report use case. Over-broad routing can misapply restrictive transformations, drop important context, or override a more appropriate skill, creating integrity and least-surprise issues in downstream handling.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill mandates Chinese output without checking the user's preferred language or documenting a hard business requirement. This can cause unintended language conversion, reduce usability, and potentially mishandle multilingual or compliance-sensitive content by forcing a locale transformation the user did not request.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest text specifies that the skill generates a Chinese R&D weekly report and the default prompt also instructs it to produce output in Chinese. This imposes a language choice by default without indicating that users can select another language or opt in to the locale constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instruction is written as a direct requirement in Chinese to generate a weekly report, with no indication that the user can choose another language or locale. This can violate language/locale policy when a skill implicitly enforces one language without opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file contains only Chinese-language content and does not indicate that the user opted into Chinese or that the skill is intentionally region-specific. The stated policy requires flagging language or locale constraints when they are imposed without user choice or clear justification.

Content

No source excerpt is available for this finding.