agent-mail
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 download and execute the official ClawLink command-line interface from the NPM registry. - [COMMAND_EXECUTION]: The skill instructs the agent to run various shell commands using the
@useclawlink/clito perform actions like login, connection, and email management (e.g.,npx @useclawlink/cli run agent-mail ...). - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data by retrieving email messages.
- Ingestion points: The
agent_mail_get_messageandagent_mail_list_messagesactions ingest external email content (sender, subject, body) into the agent context (SKILL.md). - Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" headers for the processed email content.
- Capability inventory: The skill uses
npxfor subprocess calls and network operations to interact with the AgentMail API (SKILL.md). - Sanitization: There is no explicit mention of sanitization or filtering of incoming email content before it is processed by the agent.
Audit Metadata