Back to skill

Security audit

carrusel-ilustrado-formula100k

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed workflow for generating illustrated Instagram carousel images, with expected use of image-generation services, local render files, and Telegram delivery.

Install only if you are comfortable with the agent using your configured image-generation provider, creating files under entregables/, rendering local HTML with Chrome headless, and sending the resulting images through Telegram. Confirm costs and output destination before running large batches.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (6)

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 252)May include surrounding context.

Si algún slide muestra una pantalla de app, generarla primero como HTML independiente:

html
<!-- mockup-[nombre].html — 1080×1350px, no necesita ser 4:5 exacto -->
<!DOCTYPE html>
<html><head>
<style>

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 252)May include surrounding context.

Si algún slide muestra una pantalla de app, generarla primero como HTML independiente:

html
<!-- mockup-[nombre].html — 1080x1350px, no necesita ser 4:5 exacto -->
<!DOCTYPE html>
<html><head>
<style>

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 464)May include surrounding context.

md
Consultar `references/guia-ilustraciones.md` para:

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The activation rule in the skill description is overly broad and can cause the agent to invoke this skill for loosely related requests based on vague variations. Overbroad auto-activation increases the chance of unintended tool use, file generation, or external API calls when the user's request did not clearly ask for this workflow.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The condition 'any carousel where the concept is abstract and needs conceptual visualization' is subjective and expansive, making accidental activation likely. In this skill, accidental activation is more dangerous because it can cascade into other skills, external image generation, local file writes, and headless browser rendering.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

Line L004 states that each illustration type includes a description in English for the Higgsfield prompt, and multiple later headings reinforce this requirement. This is a natural-language locale constraint presented as a default without user opt-in or explanation of why English is required.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.