grant-writing-framework
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of Markdown-based instructions and templates. No scripts, binaries, or automated tools are included in the skill package.
- [SAFE]: All external resources mentioned (such as Grants.gov, Candid, and the National Council of Nonprofits) are well-known, authoritative sources in the grant-writing domain and are provided for informational reference only.
- [SAFE]: The skill defines a surface for indirect prompt injection through placeholders in its grant templates, but the risk is absent as the skill has no associated capabilities or tools to exploit. Evidence: Ingestion points are placeholders in SKILL.md; boundary markers are absent; capability inventory is empty (no tools or scripts); sanitization is absent.
- [SAFE]: No evidence of prompt injection, obfuscation, or credential harvesting was found in the instructions or metadata.
Audit Metadata