update-rfc
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed exclusively of natural language instructions for managing documentation. It lacks any command execution, network activity, or credential handling mechanisms.
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for processing external content from RFCs and implementation records, creating a surface for indirect prompt injection. This risk is addressed by the skill's specific focus on documentation reconciliation and instructions to preserve the original intent of the design. Ingestion points: RFC documents and implementation references such as PRs and code files. Boundary markers: Explicit instructions are included to preserve the document's agreed intent and established identity. Capability inventory: The skill is limited to reading repository files and updating markdown documentation. Sanitization: None explicitly defined.
Audit Metadata