walrus-sites-publishing

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a workflow where the agent ingests data from local user-controlled sources, which represents an indirect prompt injection surface.
  • Ingestion points: The agent is instructed to read content from a local dist/ directory and a ws-resources.json configuration file as part of the deployment process (SKILL.md).
  • Boundary markers: No boundary markers or specific instructions to ignore embedded commands are specified for the ingested content.
  • Capability inventory: The skill enables the agent to execute shell commands using the site-builder CLI, including deployment, update, and destruction operations.
  • Sanitization: No content sanitization or validation mechanisms are described for the files before they are processed by the deployment tool.
  • [SAFE]: The skill exclusively references official tools and documentation from the vendor.
  • The prerequisites section instructs the installation of site-builder and walrus via suiup, the official Sui toolchain manager.
  • External documentation and source code links point to official Mysten Labs repositories on GitHub and the official documentation at wal.app.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 04:57 AM
Security Audit — agent-trust-hub — walrus-sites-publishing