Back to skill

Security audit

邮件约时间与回信草稿助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed email scheduling and draft assistant with scoped handling of email-thread inputs, optional user-authorized AI-HIVE use, and no evidence of hidden persistence or destructive behavior.

Install only if you are comfortable using a Chinese-language workflow for email scheduling. Provide only the specific thread or exported text needed for the task, review drafts before sending, and separately approve any upload, paid AI-HIVE call, message sending, payment, deletion, or business-system change.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (6)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared behavior is email scheduling and draft generation, but the referenced execution path includes offline validation, artifact checks, hashing, and secret-like string detection that are not clearly disclosed in the top-level skill description. This mismatch can mislead operators about what the skill actually does, causing them to approve or invoke it under false assumptions and potentially expose unrelated local artifacts to inspection.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding

The skill appears to rely on file-reading behavior but does not declare any explicit tool scope or allowed-tools boundary. Missing scope declarations weaken least-privilege controls and make it harder for the host agent to restrict what the skill may access, increasing the chance of unintended data exposure from local files or referenced artifacts.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill uses broad trigger phrases such as general email assistant and executive assistant scenarios, which can cause over-activation for common user requests. Over-broad activation increases the chance that the skill is invoked in contexts where users did not intend mailbox-thread processing or external-tool workflows, expanding unnecessary access to sensitive communications.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The entire skill description and operating instructions are written only in Chinese, and there is no statement that the user may choose another language or that the skill is intentionally limited to a Chinese-speaking context. Under the policy, language constraints should be optional or clearly justified rather than implicitly enforced.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown workflow is written exclusively in Chinese, including headings, operational instructions, and examples. Under the policy rule for natural-language violations, forcing a specific language without offering the user a language or locale choice can be a policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The natural-language note is written only in Chinese and provides important user guidance, which can impose a language-specific requirement on users without opt-in. The file does not indicate that this skill is region-specific or offer an alternative language choice, so it may violate language/locale policy expectations.

Content

No source excerpt is available for this finding.