Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md | 文档与理论文本 | 本 `SKILL.md`、`README.md`、其中「理论依据」段与一切理论表述 | **不在 MIT 覆盖范围内**：保留所有权利（All rights reserved） |
Security audit
ardot-mobile-app-multi-screen
Security checks for vulnerabilities and agentic risk
Overview
This is a document-only design skill for Ardot mobile app screen mockups; its main issue is overly broad activation wording, not malicious behavior.
Install only if you want an Ardot-oriented mobile multi-screen design helper. Be aware that its activation terms are broad and its license statements are inconsistent, so review the licensing text before redistributing the package or relying on the manifest's MIT label.
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
- 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
Findings (5)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The trigger keywords are extremely generic terms like "mobile", "app", "multi", and "screen", which can match a wide range of ordinary conversations unrelated to this specific skill. That increases the chance of unintended activation, causing the agent to apply this skill in the wrong context and potentially override more appropriate instructions or workflows.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The statement that any user question in any supported language can trigger the skill makes activation effectively unconstrained. This broad routing rule can cause accidental invocation on unrelated requests, increasing prompt-scope confusion and making the skill behave as a catch-all instead of a specialized design aid.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The manifest includes very broad trigger phrases such as generic UI/prototyping terms and English equivalents like 'mobile app screens' and 'multi-screen mockup' without clear activation boundaries. This can cause the skill to activate in unrelated design conversations, leading to unintended routing, prompt collisions, or over-application of the skill's instructions rather than a direct security compromise.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 84% confidence
- Finding
The leading notice is presented primarily in Chinese while the file otherwise contains the standard MIT license in English, and it does not offer an explicit language choice or explain a locale-specific requirement. This can be a natural-language policy concern because it imposes a language expectation for key licensing guidance without opt-in.
- Content