internal-email-composer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [PROMPT_INJECTION] (SAFE): The instructions define a specific persona for email writing and do not include any attempt to bypass LLM safety guidelines or override system prompts.
- [DATA_EXFILTRATION] (SAFE): There are no commands or patterns associated with accessing local files or sending data to external servers.
- [REMOTE_CODE_EXECUTION] (SAFE): The skill does not download or execute any remote scripts or packages.
- [COMMAND_EXECUTION] (SAFE): No system commands, shell scripts, or subprocess calls are present in the skill definition.
- [Indirect Prompt Injection] (SAFE): The skill processes user input but lacks any capabilities (such as file-write or network-send) that could be exploited via malicious input data.
Audit Metadata