Back to skill

Security audit

Turn quotes and reflections from books or films into polished shareable check-in posters.

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward poster-generation helper that uses the Mew design API and discloses the main privacy-relevant data flows.

Before using it, understand that your poster text, any provided image URLs, optional name or watermark text, and the Mew API key will be used with Mew's external API. Avoid sending sensitive personal content, and only approve temporary image uploads if you are comfortable sharing that image with an external host.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
95% confidence
Finding

The install instruction is embedded in the skill metadata description and uses a natural-language phrase that could be echoed or paraphrased during normal conversation. Because it lacks strong scoping or confirmation requirements, an agent may treat ordinary user help requests as consent to install code from an external source, creating a prompt-triggered supply-chain risk.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The example requests include broad phrases like 'Help me install this ClawHub skill' and 'Install this skill and then use it,' which have weak boundaries and can match ambiguous user intent. In a skill ecosystem, this increases the chance of unintended installation or activation of external functionality without sufficiently specific user authorization.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

The direct call to api.mew.design at this location confirms an outbound network transmission path to a third-party API. In context this is expected for image generation, but it is still security-relevant because sensitive prompts, uploaded asset references, and authentication material cross trust boundaries and could be exposed through logs, misuse, or user misunderstanding.

Content

Scanner excerpt · SKILL.md (reported line 255)May include surrounding context.

For stage 1, call the official Mew image-process API directly:

bash
curl -sS -X POST "https://api.mew.design/open/api/image/process" \
  -H "Content-Type: application/json" \
  -H "x-api-key: USER_PROVIDED_KEY" \
  -d '{

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

The direct call to api.mew.design at this location confirms an outbound network transmission path to a third-party API. In context this is expected for image generation, but it is still security-relevant because sensitive prompts, uploaded asset references, and authentication material cross trust boundaries and could be exposed through logs, misuse, or user misunderstanding.

Content

Scanner excerpt · SKILL.md (reported line 255)May include surrounding context.

For stage 1, call the official Mew image-process API directly:

bash
curl -sS -X POST "https://api.mew.design/open/api/image/process" \
  -H "Content-Type: application/json" \
  -H "x-api-key: USER_PROVIDED_KEY" \
  -d '{

External Transmission

Medium
Category
Data Exfiltration
Confidence
89% confidence
Finding

The second-stage design generation call also sends user content and asset image URLs to an external service, again with an API key. This is not inherently malicious, but it is a true security concern because the final composition step may include personal reflections, names, watermarks, and image assets that leave the local environment.

Content

Scanner excerpt · SKILL.md (reported line 269)May include surrounding context.

For stage 2, call the official Mew design-generate API directly:

bash
curl -sS -X POST "https://api.mew.design/open/api/design/generate" \
  -H "Content-Type: application/json" \
  -H "x-api-key: USER_PROVIDED_KEY" \
  -d '{