Security audit

create-favicon

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently creates website favicons using a disclosed external service and local file edits.

Branding inputs sent to favicongenerator.io leave your environment; avoid confidential names or designs unless that is acceptable. Review returned shell commands and HTML before applying them. The external service's live responses and privacy practices were not verified.

A.I.G

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

SkillSpector

Vulnerability Patterns

Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
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 (1)

The workflow sends user-selected branding to a third-party API without a privacy warning.

Medium

Category: Output Handling
Confidence: 90% confidence
Finding: The workflow instructs the agent to send brand initials, text, or symbol searches to favicongenerator.io; lines 40–41 also permit sending the site's name. Although the external service is identified, the skill does not warn that these inputs leave the user's environment, and describing the API as read-only does not address that disclosure.
Content: No source excerpt is available for this finding.