writing-assistant
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Overall Security] (SAFE): The skill consists exclusively of markdown instruction files. There are no scripts (.py, .js, .sh), binary files, or configuration files that could execute commands on the host system.
- [Data Exposure & Exfiltration] (SAFE): No network operations (curl, wget, fetch) or access to sensitive local file paths (e.g., ~/.ssh, .env) were detected. The skill only interacts with local files created during the session for tracking writing progress.
- [Remote Code Execution] (SAFE): There are no external downloads or remote script executions. The skill does not install any third-party packages.
- [Indirect Prompt Injection] (LOW): While the skill ingests untrusted user input (thoughts and ideas) to generate articles, it lacks exploitable capabilities like command execution or network access. The risk is limited to content manipulation within the generated text.
Audit Metadata