Back to skill

Security audit

TANGSUAN1994

Security checks for vulnerabilities and agentic risk

Overview

The skill has a clear knowledge-base purpose, but it writes persistent records to a fixed enterprise sheet and documents an unsafe shell-command pattern using user-controlled fields.

Review carefully before installing. Only use this skill with a known WeCom sheet you control or trust, confirm the destination before each write, and avoid executing the documented command through a shell with raw user-provided titles, URLs, categories, or summaries.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:36
Finding

Shell Command Injection Through Unescaped User-Controlled Fields

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger conditions are broad enough that ordinary mentions of '知识库', generic requests to archive information, or simply sending a document link could invoke a workflow that writes data into a fixed enterprise smart sheet. In this skill, unintended invocation is more dangerous because the action is persistent and targets a specific shared repository, creating a risk of accidental data entry, privacy leakage, or unauthorized record creation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill hardcodes a specific enterprise document ID, sheet ID, and table link, but does not prominently warn users that their provided titles, summaries, categories, and URLs will be written into that fixed shared destination. This can lead to silent exfiltration of potentially sensitive links or document descriptions into an organizational knowledge base, especially if users assume the assistant is only summarizing rather than persisting data.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The natural-language instructions and examples are entirely in Chinese and specify response phrasing in Chinese, but they do not state that the skill is intentionally limited to a Chinese-speaking or region-specific context. Under the policy, forcing a specific language without user opt-in can be a locale/language policy issue.

Content

No source excerpt is available for this finding.