Desing mobile apps

• Outcome: Review
• Latest audit: Sep 11, 2026 · 1:11 AM UTC
• Version: 1.0.4

Overview

This skill mostly matches its Sleek mobile-design purpose, but it can send broad design prompts to Sleek and exposes project deletion without explicit confirmation guidance.

Install only if you intend Codex to use Sleek for mobile app design work. Use the narrowest possible Sleek API key, avoid sending sensitive prompts or private image URLs, and require explicit confirmation before any project deletion.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Tool Misuse: Tool Parameter Abuse, Chaining Abuse, Unsafe Defaults
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Context Leakage

High

• Category: Data Exfiltration
• Confidence: 85% confidence

Finding

Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

Content

Scanner excerpt · SKILL.md (reported line 39)May include surrounding context.

md

| `projects:write`  | Create / delete projects     |
| `components:read` | List components in a project |
| `chats:read`      | Get chat run status          |
| `chats:write`     | Send chat messages           |
| `screenshots`     | Render component screenshots |

Create a key with only the scopes needed for the task.

Context Leakage

High

• Category: Data Exfiltration
• Confidence: 85% confidence

Finding

Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

Content

Scanner excerpt · SKILL.md (reported line 90)May include surrounding context.

md

| `projects:write`  | Create / delete projects     |
| `components:read` | List components in a project |
| `chats:read`      | Get chat run status          |
| `chats:write`     | Send chat messages           |
| `screenshots`     | Render component screenshots |

Create a key with only the scopes needed for the task.

Tool Parameter Abuse

High

• Category: Tool Misuse
• Confidence: 95% confidence

Finding

The skill exposes a destructive DELETE endpoint for projects while the skill's broad activation and workflow guidance do not require strong confirmation or ownership checks before destructive operations. If the skill is triggered in error or manipulated by ambiguous user input, it could delete user projects irreversibly, causing significant loss of work.

Content

Scanner excerpt · SKILL.md (reported line 142)May include surrounding context.

http

GET    /api/v1/projects/:projectId
DELETE /api/v1/projects/:projectId   → 204 No Content

---

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 93% confidence

Finding

The skill description is activated by very broad phrases like 'design a mobile app', 'build UI', and generic interaction requests, which can overlap with many normal user intents. Over-broad routing can cause this skill to trigger unexpectedly and send user prompts or project data to an external service without sufficiently clear user intent, increasing the chance of unintended data disclosure or destructive actions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.