Back to skill

Security audit

火星文转换器

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local novelty text converter for Chinese “mars text” and does not show hidden access, network use, persistence, or unsafe authority.

Reasonable to install if you want a Chinese 火星文 converter. Be aware that the documentation and CLI messages are in Chinese, and the optional --json flag currently appears broken until the publisher adds the missing json import.

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 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 (7)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The README is entirely in Chinese and presents the skill as operating only on Chinese text, without offering any language choice or noting that the skill is intentionally limited to Chinese speakers. Under the policy, forcing a specific language or locale without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The display name and description specify operation on Chinese text only, with no indication that the user can choose language or that the locale restriction is optional. This can be a natural-language policy concern when a skill implicitly enforces a specific language without documenting user opt-in or justification.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill presents itself as a text converter and its usage string explicitly documents a --json output mode. However, when --json is used, the code calls json.dumps(...) at L815 without importing json, so the advertised behavior fails at runtime with a NameError instead of returning converted text.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This manifest describes what the skill does but provides no explicit trigger phrases, invocation boundaries, or exclusion conditions. For manifest files, missing specificity on trigger scope can make activation behavior ambiguous and increase the chance of unintended invocation.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The inline documentation says this is "火星文转换器 v2.0" with "700+ 汉字映射", while the manifest describes v2.1 with 611 mappings after cleanup. This is not just incomplete documentation: it actively describes a different version and capability footprint than the skill claims externally, creating intent/documentation divergence.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This code file contains natural-language documentation entirely in Chinese, presenting the tool description in a single fixed language without any opt-in, alternative locale, or justification for a locale restriction. Under the policy rule for language/locale constraints, this is a natural-language policy issue because the skill does not offer the user a language choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The command-line usage string is user-facing natural language and is hard-coded in Chinese, with the same pattern continuing in other printed status messages. Because the script gives no language selection or documented locale limitation, it forces a specific language without user opt-in.

Content

No source excerpt is available for this finding.