zk-steward

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references an external GitHub repository (github.com/mikonos/zk-steward-companion) for companion skills and scripts. It instructs the user to clone or copy these resources into their project environment to enable the full ZK Steward workflow.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it is designed to ingest and process untrusted external data (such as articles, reports, and papers) for deep-reading and note-taking tasks.
  • Ingestion points: Processes articles, reports, papers, and user-provided notes (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing workflows.
  • Capability inventory: File system read and write operations within the workspace (SKILL.md).
  • Sanitization: No evidence of input validation or content sanitization before the agent processes external text.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 02:36 AM
Security Audit — agent-trust-hub — zk-steward