mo-writing-voice-system
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill processes external text inputs such as essays, emails, and posts provided by the user, which presents an indirect prompt injection surface.
- Ingestion points: Untrusted text is ingested via placeholders defined in assets/voice-primer-prompt.md and instructions in SKILL.md.
- Boundary markers: The skill uses simple brackets like [paste draft] to demarcate user input, which offers minimal protection against adversarial text.
- Capability inventory: The agent is limited to text generation and scoring, with no access to dangerous tools such as shell execution, network requests, or file system writes.
- Sanitization: There is no evidence of input validation or content escaping for the processed text.
- [NO_CODE]: The skill consists entirely of Markdown instructions and configuration templates. It does not include any executable scripts, libraries, or binary files, significantly reducing the potential for malicious code execution.
Audit Metadata