postmark
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of @membranehq/cli, which is the official CLI tool for the Membrane platform and is maintained by the skill author.
- [COMMAND_EXECUTION]: The skill executes membrane CLI commands to perform operations like logging in, searching for connectors, and running Postmark actions. These commands are executed locally within the Membrane environment.
- [PROMPT_INJECTION]: A low-risk surface for indirect prompt injection exists because the skill processes untrusted data fetched from the Postmark API.
- Ingestion points: Data is ingested from Postmark via actions like search-outbound-messages, get-bounce, and get-outbound-message-details (SKILL.md).
- Boundary markers: Absent; the skill does not define specific delimiters or isolation instructions for external data retrieved from the API.
- Capability inventory: The skill can send emails and perform arbitrary API requests through the Postmark proxy (SKILL.md).
- Sanitization: Absent; no explicit validation or filtering of external Postmark data is defined before the agent processes it.
Audit Metadata