mailgun
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
@membranehq/clitool from the NPM registry to manage authentication and execute actions. This is a vendor-provided tool corresponding to the skill's authoring organization. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources including email logs (
get-events), mailing list member information, and email template content. - Ingestion points: Actions like
get-events,list-mailing-list-members, andget-templateretrieve data from Mailgun. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' markers when processing the retrieved data.
- Capability inventory: The agent has the capability to send emails (
send-email), create webhooks, and perform arbitrary API requests viamembrane request. - Sanitization: There are no explicit instructions for the agent to sanitize or validate the content retrieved from Mailgun before processing or using it in subsequent actions.
Audit Metadata