yutori-api-monitor

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill sets up an automated ingestion pipeline for untrusted external data, which is a surface for indirect prompt injection.
  • Ingestion points: The scout query structure in SKILL.md targets external sources such as official changelogs, developer blogs, and GitHub releases.
  • Boundary markers: No delimiters or isolation instructions are present in the query template to separate external data from agent instructions.
  • Capability inventory: The skill uses the create_scout tool to fetch, summarize, and report on external content every 12 hours.
  • Sanitization: There is no defined process for validating or sanitizing the content retrieved from external sites before it is summarized.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 12:17 AM