create-rfc
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill scans local directories using
lsorGlobto identify existing RFC files and calculate the next sequential number for the new document, as described inreferences/numbering.md.- [INDIRECT_PROMPT_INJECTION]: The skill functions as a template filler that ingests user-provided text, which creates an inherent surface for indirect prompt injection. - Ingestion points: User-supplied context for the RFC title, background, and options gathered during the first step of the process (
references/process.md). - Boundary markers: None. The
templates/rfc.mdfile uses standard markdown structure but does not include explicit delimiters or safety instructions to isolate user-provided data. - Capability inventory: The skill uses directory listing commands (
ls) and file system write operations to create the generated markdown files. - Sanitization: There are no instructions for sanitizing or escaping user-provided text before it is interpolated into the markdown template.
Audit Metadata