resend
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npx @useclawlink/clito fetch and execute the ClawLink command-line interface. This package is provided by the skill vendor to facilitate the integration. - [COMMAND_EXECUTION]: Instructions guide the agent to run shell commands using the ClawLink CLI for authentication (
login), service connection (connect), and executing Resend operations (run). - [INDIRECT_PROMPT_INJECTION]: The skill processes data from Resend (emails, templates, contacts) that may originate from third parties, creating a potential surface for indirect prompt injection.
- Ingestion points: Retrieves content from Resend via actions like
resend_get_emailandresend_list_contacts(SKILL.md). - Boundary markers: The instructions explicitly state to "confirm with the user before any write," serving as a manual security boundary.
- Capability inventory: The agent can send emails and modify audience/contact lists using the CLI.
- Sanitization: The skill does not define specific sanitization or filtering logic for the data retrieved from Resend.
Audit Metadata