skills/bankrbot/skills/Indexing/Gen Agent Trust Hub

Indexing

Pass

Audited by Gen Agent Trust Hub on Jul 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill configuration and setup instructions reference content from ethskills.com and a plugin from a third-party GitHub repository (austintgriffith/ethskills).\n- [COMMAND_EXECUTION]: The catalog.json file defines an install command using curl to download a remote markdown file.\n- [PROMPT_INJECTION]: The setup process instructs the agent to read instructions from a remote URL (https://ethskills.com/indexing/SKILL.md) before performing tasks, making it vulnerable to indirect prompt injection where external content could alter agent behavior.\n
  • Ingestion points: catalog.json and SKILL.md reference https://ethskills.com/indexing/SKILL.md\n
  • Boundary markers: None provided in the instructions.\n
  • Capability inventory: Querying onchain data (network access).\n
  • Sanitization: No sanitization or validation of the remote content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 5, 2026, 02:12 PM
Security Audit — agent-trust-hub — Indexing