oneshot-email
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides tools for reading inbound emails which ingests untrusted data into the agent's execution context.
- Ingestion points: The
agent.inboxListandagent.inboxGetmethods inSKILL.mdretrieve external email content. - Boundary markers: The instructions do not specify any delimiters or warnings for the agent to ignore instructions embedded within the email bodies.
- Capability inventory: The skill provides capabilities for sending emails (
agent.email) and managing sending domains (pauseDomain,resumeDomain) which could be misdirected by malicious email content. - Sanitization: There is no mention of sanitization or validation of inbound email content before it is exposed to the agent.
Audit Metadata