ClawHub
Back to skill

Security audit

智能报告生成器

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent report generator, but its default Feishu output with auto-send enabled could publish sensitive business reports without clear per-run user review.

Install only if you intend to generate Chinese-language business reports and are comfortable configuring Feishu output carefully. Disable auto-send or require preview and explicit approval before sending reports, especially when source data may contain confidential sales, KPI, task, customer, or internal business information.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill advertises automatic report generation and output to external systems or local files, but it does not clearly warn users that their data may be written to disk or sent to Feishu automatically. This can cause unintended disclosure of sensitive business data, especially when reports are generated from spreadsheets, JSON, databases, or other aggregated sources containing confidential information.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
### Smart Reporter
- Default Output: feishu_doc
- Report Timezone: Asia/Shanghai
- Auto Send: true
```

---
Confidence
95% confidence
Finding
The configuration explicitly enables 'Auto Send: true', which allows the skill to autonomously publish generated reports to Feishu without an explicit per-run approval step. In a reporting skill that processes business data from files, tables, or databases, this increases the risk of accidental exfiltration, oversharing, or sending incorrect or sensitive analysis to external recipients.

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
The description is written only in Chinese, which can bias invocation behavior toward a specific language without explicit user preference or opt-in. This may cause mismatched user interactions, confusion, or unintended execution in multilingual environments where the agent should respect the user's language context.

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
This markdown template is entirely written in Chinese, including all section headers and the auto-generation notice, which indicates the skill produces reports in a fixed language. The file does not provide any indication that the user can choose another language or that this locale restriction is optional or justified.

Natural-Language Policy Violations

Low
Confidence
84% confidence
Finding
The description and primary documentation are presented entirely in Chinese, indicating a language-specific experience, but there is no statement that the skill is China-region-specific or that users may choose another language. The policy requires avoiding forced language or locale constraints unless users can opt in or the restriction is clearly justified.

Vague Triggers

Low
Confidence
91% confidence
Finding
The manifest description is very broad and does not clearly limit when the skill should be invoked. In agent ecosystems, overly broad descriptions can cause inappropriate routing or over-invocation, leading the skill to process data or generate outputs in contexts the user did not intend.

Natural-Language Policy Violations

Low
Confidence
95% confidence
Finding
The template headings and fixed text are entirely in Chinese, which implies the generated report will be produced in that language by default. Under the policy rules, forcing a specific language without offering user choice or documenting a justified locale constraint is a natural-language policy violation.

Static analysis

No suspicious patterns detected.