writing-in-my-voice
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for text formatting and stylistic preferences. It does not contain any executable scripts, binaries, or configuration files that interact with the system.
- [SAFE]: No external tools or system capabilities are requested in the frontmatter or used in the instructions, eliminating the risk of command execution, privilege escalation, or data exfiltration.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and rewrite user-provided content. While this represents an ingestion surface for potential indirect prompt injection, the skill possesses no exploitable capabilities (no network access, file system access, or shell tools). Furthermore, the instructions explicitly command the agent to preserve the original purpose, format, and technical meaning of the content, which serves as an inherent constraint against malicious re-instruction.
Audit Metadata