Back to skill

Security audit

Architecture Diagram HTML/SVG

Security checks for vulnerabilities and agentic risk

Overview

This skill is a static diagram-writing aid with no hidden execution, persistence, credential use, or unrelated authority.

Installers should expect the skill to help create and edit local standalone HTML/SVG diagram files. If using it for a non-Chinese audience, explicitly request the desired language for labels.

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
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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
Findings (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This manifest-style JSON contains natural-language prompts and expectations that require Chinese labels and output, which imposes a specific language/locale by default. The file does not indicate user opt-in, alternative language support, or a documented region-specific justification for the constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The prompt and expected output explicitly require Chinese content, creating a fixed language policy in natural-language instructions. Because no opt-in or locale rationale is provided in the file, this matches the policy-violation criterion for forced language selection.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The natural-language requirements specify Chinese labels and readability, which forces a locale-specific output format. The file provides no indication that users can opt in to Chinese or select another language, and no region-specific compliance reason is stated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The prompt and expected output require Chinese-labeled HTML/SVG output, representing a natural-language locale restriction. Since the file does not offer a language choice or explain a necessary Chinese-only scope, it falls under the language policy violation rule.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The instruction says to prefer clear Chinese labels when the audience is Chinese-speaking, which sets a language behavior by default rather than explicitly offering a user choice. Under the policy, locale or language constraints should be opt-in or clearly justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.