proposal-writer
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill focuses on structured text generation for business documents and does not contain any malicious code, command execution, or data exfiltration logic.
- [SAFE]: All external URLs referenced in the documentation point to legitimate business and government resources such as HubSpot, the Korean National Tax Service, and market research firms.
- [SAFE]: The skill provides security-positive guidance, specifically recommending the use of a legal triage skill (moai-legal:nda-triage) when handling documents subject to Non-Disclosure Agreements (NDA).
- [SAFE]: The skill's instructions encourage a 'Human-in-the-Loop' approach, emphasizing that all AI-generated outputs must be reviewed by a person before final use.
- [PROMPT_INJECTION]: The skill includes instructions to ingestion untrusted data from RFPs and customer requirements (File: SKILL.md). While it lacks explicit boundary markers or sanitization steps to isolate this data, its operations are restricted to generating textual content and advising on further document processing, presenting no immediate technical risk.
Audit Metadata