Back to skill

Security audit

Cn Temperature Converter

Security checks for vulnerabilities and agentic risk

Overview

This is a simple local temperature converter with unrelated promotional links in its documentation, but no evidence of hidden execution, data access, persistence, or privilege use.

This skill appears safe to use for local temperature conversion. Be aware that the documentation contains unrelated AISoBrand marketing links in Chinese; only follow those links if you trust that external site.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill is presented as a pure temperature-conversion utility, but the documentation injects unrelated promotional links to an external website. This creates a documentation/intent mismatch and can be abused for traffic diversion, affiliate-style promotion, or social-engineering exposure even though no code execution is involved.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

Outbound promotional links unrelated to the skill's stated purpose increase user exposure to third-party content without functional justification. In an agent-skill ecosystem, such links are risky because users may treat bundled documentation as trusted and follow links that were not needed for operation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The markdown is primarily in English, but the closing promotional section switches to Chinese-only text and links without any user opt-in or explanation that the skill is intended for a Chinese-speaking audience. This creates a natural-language locale inconsistency that can violate organizational language/locale policy when users are not given a choice.

Content

No source excerpt is available for this finding.