better-auth-profile

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • EXTERNAL_DOWNLOADS (MEDIUM): The skill provides a bash command using curl to fetch content from https://fullstackrecipes.com/api/recipes/better-auth-profile. This domain is not recognized as a trusted source. Content retrieved from external URLs can be modified by third parties to include malicious scripts or configuration changes.
  • PROMPT_INJECTION (LOW): This skill is vulnerable to Indirect Prompt Injection (Category 8) because it instructs the agent to process data from an external resource. * Ingestion points: recipe://fullstackrecipes.com/better-auth-profile and https://fullstackrecipes.com/api/recipes/better-auth-profile in SKILL.md. * Boundary markers: Absent. * Capability inventory: The skill's purpose ('Add a complete account settings page') suggests the agent will perform file system writes or code generation based on the external input. * Sanitization: No sanitization or validation of the fetched 'recipe' is performed.
  • COMMAND_EXECUTION (LOW): The skill includes a bash code block containing a curl command in SKILL.md. Executing commands provided in a skill from an untrusted author is a risk.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 05:25 PM