mandrill
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the
@membranehq/clipackage from the npm registry. This tool is provided by the skill author to facilitate interaction with the Membrane platform and Mandrill API. - [COMMAND_EXECUTION]: The skill requires the execution of multiple shell commands using the
membraneCLI, includinglogin,connection ensure,action list, andaction run. These are used to manage authentication and execute transactional email tasks. - [INDIRECT_PROMPT_INJECTION]: The skill processes transactional email data from Mandrill, which could potentially contain malicious instructions intended to influence the agent.
- Ingestion points: External data enters the agent context through the JSON output of the
membrane action runandmembrane requestcommands (SKILL.md). - Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the Mandrill data provided in the skill.
- Capability inventory: The agent has the ability to execute CLI commands and make arbitrary network requests through the Membrane proxy (SKILL.md).
- Sanitization: No sanitization or validation of the API response content is mentioned in the skill instructions.
Audit Metadata