article-writer
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill consists entirely of Markdown instructions and persona definitions. It does not contain any Python scripts, Node.js code, shell commands, or binary executables.
- [REMOTE_CODE_EXECUTION] (SAFE): There are no instructions or patterns related to downloading or executing remote code or scripts.
- [DATA_EXFILTRATION] (SAFE): No network operations (curl, wget, fetch) or access to sensitive local file paths (credentials, ssh keys) were found.
- [PROMPT_INJECTION] (SAFE): The instructions are focused on creative writing style and content structure. No patterns were detected that attempt to override system safety filters or extract system prompts.
- [INDIRECT_PROMPT_INJECTION] (LOW): The skill is designed to process external inputs (Source, Analysis, Outline). While these are untrusted data sources, the skill's only capability is generating a Markdown text draft for display. It lacks the ability to execute code, perform network requests, or modify the underlying system, which limits the risk to purely content-based influence.
Audit Metadata