research-proposal-writer
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: No patterns of instruction override, safety bypass, or role-play injection were detected. The skill maintains a consistent instructional tone focused on academic writing support.
- [DATA_EXFILTRATION]: No sensitive file paths, environment variables, or hardcoded credentials are referenced. The skill does not perform network operations to untrusted domains.
- [REMOTE_CODE_EXECUTION]: There are no commands or instructions that download or execute external scripts. All external links in the documentation point to legitimate academic organizations (DARPA, MIT, SSRC, PLOS).
- [COMMAND_EXECUTION]: The skill does not use subprocesses, shell commands, or dynamic context injection patterns (e.g., the !command syntax).
- [EXTERNAL_DOWNLOADS]: External links are provided for reference only. They point to well-known academic and government domains which are considered safe for the intended use case of research guidance.
Audit Metadata