skills/hairyf/blockchain-skills/eips/Gen Agent Trust Hub

eips

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing the eipw validation tool using the Rust package manager via cargo install eipw. This is a standard procedure for authors within the Ethereum development community to ensure their proposals meet structural requirements.
  • [COMMAND_EXECUTION]: The documentation includes examples of running the eipw command-line tool to validate local EIP files against the official specification. These commands are intended for development and quality assurance purposes.
  • [INDIRECT_PROMPT_INJECTION]: The skill describes how an agent should process and reference EIP documents, which are external files formatted in Markdown and YAML. This ingestion of third-party content represents a standard attack surface for indirect prompt injection if the source files are untrusted.
  • Ingestion points: The agent is directed to read and resolve EIP specifications from the sources/eips/EIPS/ directory.
  • Boundary markers: No specific delimiters or instructions to ignore embedded commands within the EIP files are provided in the skill instructions.
  • Capability inventory: The skill references the ability to execute the eipw tool for file validation.
  • Sanitization: The skill relies on the eipw tool for structural validation but does not describe methods for sanitizing the semantic content of proposals against adversarial instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 12:16 PM