create-rfc
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill acts as a documentation assistant, providing structured templates for RFCs. It contains no scripts, binaries, or command-line instructions. All referenced resources target the official repository of the author on a well-known service.
- [NO_CODE]: The skill consists entirely of Markdown instructions and templates, with no functional code or scripts provided in the distribution.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided text to populate RFC sections. While this creates a standard injection surface, the skill lacks sensitive tools or network capabilities that could be abused via malicious data ingestion.
- Ingestion points: User-provided descriptions of proposals, assumptions, and criteria in the interactive workflow defined in SKILL.md.
- Boundary markers: None explicitly defined in the templates to separate user data from instructions.
- Capability inventory: No subprocess calls, network operations, or file-writing tools are requested or used across the instructions or template files.
- Sanitization: No specific sanitization or filtering logic is present for user-supplied content.
Audit Metadata