Skills
skills/1nfsh/skills/logo-design-guide/Gen Agent Trust Hub

logo-design-guide

Fail

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • REMOTE_CODE_EXECUTION (CRITICAL): The 'Quick Start' section includes the command curl -fsSL https://cli.inference.sh | sh. This pattern pipes remote content directly into the shell for execution. Since 'inference.sh' is not a trusted domain, this represents a severe risk of unverified remote code execution.- EXTERNAL_DOWNLOADS (MEDIUM): The skill uses npx skills add inference-sh/skills to download additional tools. These dependencies are from an untrusted source and lack version pinning or integrity verification.- COMMAND_EXECUTION (MEDIUM): The skill's allowed-tools configuration permits the Bash tool to execute any command starting with infsh. Because this CLI tool is installed via an untrusted script, it grants broad and unverified execution capabilities to the agent.- PROMPT_INJECTION (LOW): The skill is vulnerable to indirect prompt injection. Evidence: 1. Ingestion points: User-provided 'prompt' text in infsh app run commands. 2. Boundary markers: Input is wrapped in single quotes within shell commands. 3. Capability inventory: Use of Bash and the infsh CLI for network and execution tasks. 4. Sanitization: No input sanitization is present, allowing potential shell breakout via malicious input in the prompt string.
Recommendations
  • HIGH: Downloads and executes remote code from: https://cli.inference.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 18, 2026, 03:12 AM
Security Audit — agent-trust-hub — logo-design-guide