skills/tw93/waza/think/Gen Agent Trust Hub

think

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs codebase analysis using standard tools (Bash, Grep, Read) to provide architectural feedback, which is consistent with its primary function.
  • [SAFE]: The skill possesses a potential indirect prompt injection surface as it processes files and commits from the codebase. Ingestion points: Reads codebase files and recent commits (SKILL.md). Boundary markers: Absent. Capability inventory: Bash, Read, Grep, Glob, WebSearch, AskUserQuestion (SKILL.md). Sanitization: Absent. This analysis surface is expected given the skill's purpose and does not involve malicious logic.
  • [SAFE]: External references, such as the installation command in the README, point to the author's official repository (tw93/Waza) and follow established platform conventions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 11:43 PM