resend

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFE
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill guides users to manage API keys through environment variables in .env.local files, which is an established security best practice for protecting secrets.\n- [DATA_EXFILTRATION]: Includes code to read local files using fs.readFileSync for email attachments. This operation is standard for the skill's primary purpose of email communication.\n- [PROMPT_INJECTION]: The skill interpolates external data into email templates, which identifies a potential surface for indirect prompt injection.\n
  • Ingestion points: Untrusted data is ingested from HTTP request bodies in Next.js API routes and Server Action arguments (e.g., email, username, message).\n
  • Boundary markers: The provided code snippets do not incorporate explicit delimiters or instructions to the agent to ignore potentially malicious instructions embedded in the user data.\n
  • Capability inventory: The skill allows for local file system access and network transmission through the Resend API.\n
  • Sanitization: The examples do not demonstrate input sanitization or HTML escaping before rendering user-provided content into email bodies.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 07:53 AM