grant-writer
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for research grant proposal drafting and review. It contains no scripts, binaries, or executable code.
- [SAFE]: No network requests or sensitive file system access are defined in the instructions.
- [SAFE]: No prompt injection, obfuscation, or data exfiltration patterns were identified.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted sponsor call text and project details. However, it lacks any executable capabilities (no file writes, network access, or shell commands), rendering the attack surface harmless.
Audit Metadata