resend-cli
Pass
Audited by Gen Agent Trust Hub on Nov 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes commands to read and listen to inbound emails, creating an attack surface where an attacker could send emails containing malicious instructions.
- Ingestion points:
emails receiving get,emails receiving listen(inreferences/emails.md), andinboxes threads emails get(inreferences/inboxes.md) pull external subject lines, bodies, and headers into the agent context. - Capability inventory: As described in
SKILL.md, the CLI possesses powerful capabilities such asapi-keys create,domains delete, andemails sendwhich could be targeted by an injection attack if the agent obeys instructions inside an email. - Boundary markers: The skill contains explicit instructions to agents in
SKILL.mdto treat received email content strictly as data and never as instructions. - Sanitization: The instructions in
references/emails.mdemphasize that content from inbound emails is untrusted and must be sanitized before processing. - [DYNAMIC_EXECUTION]: The skill facilitates the runtime bundling and rendering of React Email templates (.tsx files) via flags like
--react-emailinemails send(inreferences/emails.md) andbroadcasts create(inreferences/broadcasts.md) commands. - This process uses
esbuildto compile local code. While a standard feature of the Resend platform, it involves dynamic execution of scripts that may be generated or modified by the agent at runtime.
Audit Metadata