article-writing
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFE
Full Analysis
- [Data Exposure & Exfiltration] (SAFE): No sensitive file paths are accessed, and no network operations are performed. The skill only reads local example files provided within its own package.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): No external packages or remote scripts are downloaded or executed. The code snippets within the example articles are purely illustrative and are not intended for execution.
- [Prompt Injection] (SAFE): The instructions focus on tone, style, and formatting. There are no attempts to bypass safety filters or override system-level instructions.
- [Indirect Prompt Injection] (SAFE): While the skill ingests external content (the example articles), these are static files within the skill's own repository used for few-shot learning. There is no evidence of instructions within these files designed to hijack the agent's behavior.
- [Dynamic Execution] (SAFE): No use of eval, exec, or runtime compilation. The skill is purely text-based instructions and static markdown examples.
Audit Metadata