resend-setup
Fail
Audited by Gen Agent Trust Hub on Feb 15, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
- External Downloads (MEDIUM): The skill fetches content from https://fullstackrecipes.com/api/recipes/resend-setup via curl. This source is not verified or trusted, posing a risk of ingesting malicious payloads.
- Indirect Prompt Injection (HIGH): The skill's primary function is to ingest untrusted external data to perform configuration tasks. * Ingestion points: Content retrieved from the fullstackrecipes.com API. * Boundary markers: Absent; the agent is simply told to fetch and use the recipe. * Capability inventory: Involved in configuring services, which implies file writes, environment variable manipulation, and setup actions. * Sanitization: None; the raw output of the fetch is provided to the agent context.
- Remote Code Execution (HIGH): Although the curl command doesn't pipe directly to bash, the instructions require the agent to setup Resend using the fetched recipe. In an AI agent context, following unvetted remote instructions to perform system configuration is functionally equivalent to remote code execution.
Recommendations
- AI detected serious security threats
Audit Metadata