nsfc-proposal-advisor
Pass
Audited by Gen Agent Trust Hub on May 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed entirely of markdown instructions without any associated scripts or executable components. No risks related to command execution or system modification were found.- [SAFE]: No network-enabled operations such as data exfiltration, remote script downloads, or external API calls are present.- [SAFE]: No hardcoded credentials, sensitive file path access, or unauthorized data exposure patterns were detected.- [PROMPT_INJECTION]: The skill is designed to process untrusted user input in the form of grant proposal drafts. While it lacks technical delimiters (boundary markers) to isolate user data from instructions, it possesses no exploitable tools or capabilities (shell, file write, network), rendering the risk of indirect prompt injection negligible.
Audit Metadata