protocol

Pass

Audited by Gen Agent Trust Hub on Sep 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch and process data from various external community resources and GitHub repositories to provide up-to-date information on Ethereum forks and EIPs. This ingestion of untrusted external data creates a potential attack surface.
  • Ingestion points: The agent is directed to read content from forkcast.org, ethereum-magicians.org, ethresear.ch, and several GitHub repositories (ethereum/EIPs, ethereum/pm, ethereum/eth-rnd-archive).
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing fetched data.
  • Capability inventory: The skill guides the agent's research behavior; while no specific dangerous tool calls are defined in the markdown, the agent's broader context likely includes browsing or file reading capabilities.
  • Sanitization: There are no instructions for sanitizing or validating the content retrieved from external URLs before it is processed by the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 5, 2026, 06:09 AM
Security Audit — agent-trust-hub — protocol