skills/zio/zio-skills/zio-knowledge/Gen Agent Trust Hub

zio-knowledge

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches documentation, sitemaps, and examples from zio.dev and github.com. These operations target the official infrastructure of the ZIO project and are consistent with the skill's primary purpose of providing accurate technical reference.
  • [INDIRECT_PROMPT_INJECTION]: The skill's core workflow relies on processing data retrieved from external URLs to inform its responses, creating a vulnerability surface for indirect instructions.
  • Ingestion points: Retrieval of llms.txt, llms-full.txt, and individual Markdown documentation pages from the zio.dev domain.
  • Boundary markers: The instructions lack explicit delimitation or warnings to the agent to treat the fetched content as untrusted data or to ignore embedded instructions within that content.
  • Capability inventory: The skill performs network read operations. It does not utilize subprocess execution, file-system writes, or administrative privileges.
  • Sanitization: There are no instructions provided for sanitizing or filtering the content retrieved from external sources before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 08:24 AM
Security Audit — agent-trust-hub — zio-knowledge