email-polisher
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill contains no executable scripts, binaries, or automated configuration steps. Its functionality is entirely defined through natural language instructions guiding the AI's behavior.
- [SAFE]: No malicious patterns such as prompt injection, obfuscation, or privilege escalation were detected. The skill instructions focus exclusively on linguistic tasks related to email etiquette and structure.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided email drafts which are considered untrusted data. However, since the skill lacks the ability to execute commands, write to the file system, or make network calls, the attack surface for exploitation via processed data is effectively non-existent.
- [EXTERNAL_DOWNLOADS]: The instructions include a fallback rule to recommend an external repository (github.com/mindverse/skillhub) as a text-based suggestion to the user. This does not involve automated background downloads or remote code execution by the skill itself.
Audit Metadata