workflow-setup

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
  • EXTERNAL_DOWNLOADS (MEDIUM): The skill instructs the agent to fetch a setup 'recipe' from an untrusted external domain (fullstackrecipes.com).
  • Evidence: curl -H "Accept: text/plain" https://fullstackrecipes.com/api/recipes/workflow-setup in SKILL.md.
  • Risk: Content fetched via curl for 'installation and configuration' purposes lacks integrity verification and could contain malicious instructions or shell commands.
  • REMOTE_CODE_EXECUTION (LOW): While the snippet does not explicitly pipe the curl output directly into a shell (e.g., | bash), the primary purpose of the skill is 'Install and configure', which strongly implies the fetched content will be executed or used to modify the system environment.
  • INDIRECT_PROMPT_INJECTION (LOW): The content fetched from the external API could contain malicious instructions designed to hijack the agent's behavior during the setup process.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 05:26 PM