Back to skill

Security audit

文员自动化助手

Security checks for vulnerabilities and agentic risk

Overview

This skill turns user-provided office notes into timestamped text work tickets and saves them locally, with storage behavior disclosed but worth noticing for sensitive workplace content.

Install only if you are comfortable with office notes and task descriptions being written to timestamped files under ./data/exports in the runtime environment. Avoid using it for confidential meeting notes, personal data, credentials, or regulated business information unless your environment's retention and access controls are acceptable.

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
  • 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 (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
80% confidence
Finding

The title, description, usage scenarios, and examples are all presented in Chinese, and the skill does not indicate that other languages are supported or that Chinese-only use is optional. This can amount to a language-policy constraint without explicit user opt-in or a documented region-specific justification.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill states that generated files are automatically saved on the server, but it does not clearly warn users that their input will be transmitted to and retained on remote storage. Users may provide meeting notes, work plans, or sensitive operational details under the false assumption that the processing is local or ephemeral.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation examples are phrased as ordinary, common workplace requests, making accidental or overly broad invocation more likely. This can cause the skill to process or save user content unexpectedly, especially because the skill also performs automatic server-side storage.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The docstring and returned status messages are entirely in Chinese, which imposes a specific language on users without any opt-in or indication that the skill is intentionally region-specific. The policy explicitly flags language or locale constraints when the skill does not offer a user choice or document a justified regional limitation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.