voice-ramble-spec-agent
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process voice transcripts, which are untrusted external inputs. It mitigates injection risks by requiring step-by-step verification, intent reconstruction for user review, and explicit confirmation before generating implementation artifacts.- [SAFE]: The skill provides a structured framework for documentation and does not perform unauthorized network requests, execute remote scripts, or access sensitive credentials. All workflows are governed by user approval.
Audit Metadata