Back to skill

Security audit

择日学技能

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese almanac date-selection skill with no sensitive access or persistence, though it appears Chinese-only and may not run as documented.

Install only if Chinese-language output is acceptable, and expect possible functionality issues because the documented python entrypoint is absent and the bundled JavaScript does not pass a syntax check. No sensitive security behavior was found in the inspected files.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This JavaScript file embeds natural-language comments and output field names exclusively in Chinese, which effectively imposes a specific language/locale on consumers of the skill. The file does not document that the skill is China-specific or provide any opt-in or language selection, matching the policy's language/locale violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest description and README content consistently require Chinese comprehension, and there is no indication that users can opt into another language or that the skill is intentionally restricted to a Chinese-language audience. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.