Back to skill

Security audit

捷帮时区转换

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward timezone utility, but it sends requests to an external service using an admin-named environment credential that is not disclosed or scoped in the skill instructions.

Install only if you are comfortable with timezone inputs being sent to jiebang.site and with the runtime providing this skill an admin-named Jiebang credential. The publisher should replace the admin key with a narrowly scoped token and document the remote domain and data sent.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
79% confidence
Finding

The skill advertises API-backed functionality and the analyzer detected network and environment access, but the manifest does not declare any explicit tool scope or permission boundaries. This creates an over-privilege and transparency problem: an agent runtime may allow broader capabilities than users or reviewers expect, increasing the risk of unintended external requests or exposure of environment-backed secrets if the implementation is compromised.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description and user-facing documentation are entirely in Chinese, with no indication that the skill supports other languages or that Chinese-only operation is a documented, justified constraint. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill retrieves an admin-scoped secret from the environment and attaches it to ordinary timezone lookup and conversion requests. For a low-risk utility, using an administrative credential greatly expands the blast radius if the remote service, logs, or request path are compromised, and it violates least-privilege by granting more authority than the feature requires.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The tool sends user-provided time and timezone inputs to an external domain together with a privileged credential, but provides no disclosure that requests leave the local environment or that authenticated backend access is being used. This creates a privacy and trust issue and increases risk because routine user inputs become linked to privileged service access and may be retained by the third-party service or intermediary logs.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

Natural-language strings in the module description and CLI interface force a specific language/locale presentation. Under the policy, locale-specific behavior should either offer a user choice or be clearly documented as a justified region-specific constraint, which is not present here.

Content

No source excerpt is available for this finding.