walrus-blob-lifecycle

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides documentation and command-line patterns for the walrus CLI, the official tool for the Walrus protocol. All documentation links and cost calculators point to official domains (wal.app) managed by the vendor, Mysten Labs.
  • [PROMPT_INJECTION]: The skill identifies a data ingestion surface via blob attributes (metadata), which could theoretically be used for indirect prompt injection if an agent processes them without sanitization. However, this is a standard feature of the protocol being documented and is not used maliciously within the skill itself.
  • Ingestion points: The walrus get-blob-attribute command in SKILL.md is used to retrieve content-controlled metadata from the Walrus network.
  • Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore embedded instructions within these attributes.
  • Capability inventory: Documented capabilities include blob deletion, lifetime extension, and metadata modification using the walrus CLI.
  • Sanitization: The skill does not provide instructions for sanitizing or escaping the data retrieved from blob attributes before use.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 07:24 AM
Security Audit — agent-trust-hub — walrus-blob-lifecycle