email-sequence-designer
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from external sources, including email platform (ESP) exports, CSV files, and user-pasted segments. While this creates a vulnerability surface where malicious instructions could be embedded in data, the skill explicitly instructs the agent to treat all such inputs as untrusted and to never follow instructions found within them.
- [COMMAND_EXECUTION]: The skill provides instructions for executing a local Python script (resend.py) to manage email broadcasts. This capability is restricted to a specific local path and includes mandatory safety controls, such as performing a dry-run by default and requiring explicit user confirmation before live execution.
Audit Metadata