Skills
Navigate
skills/bankrbot/skills/Frontend Playbook/Gen Agent Trust Hub

Frontend Playbook

Fail

Audited by Gen Agent Trust Hub on Jul 5, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's install.command and setup instructions use curl to fetch content from https://ethskills.com/frontend-playbook/SKILL.md. This establishes a dependency on an external, unverified domain for the skill's core instructions.
  • [REMOTE_CODE_EXECUTION]: The setup section contains a command to install a plugin from a third-party GitHub repository (https://github.com/austintgriffith/ethskills). Installing plugins from unverified personal repositories allows for the execution of arbitrary code within the agent's environment.
  • [PROMPT_INJECTION]: The skill explicitly directs the user to instruct the agent to read an external URL (https://ethskills.com/frontend-playbook/SKILL.md). This creates an indirect prompt injection vulnerability, as the content of the remote file can be modified by the provider to include instructions that override the agent's default behavior or safety constraints.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Jul 5, 2026, 02:11 PM
Security Audit — agent-trust-hub — Frontend Playbook