related-work-writing
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions and reference materials focus entirely on academic writing guidelines. There are no instances of command execution, network requests, or attempts to access sensitive user data.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external inputs such as paper drafts and literature notes ($0 and $1). While this introduces an external data surface, the skill does not possess any dangerous capabilities (e.g., shell access, file writing, or network operations) that could be exploited via malicious content in the processed papers. The ingestion points are clearly defined as user-provided drafts and notes, and the output is limited to text generation for academic writing.
Audit Metadata