Skills
skills/bankrbot/skills/Testing/Gen Agent Trust Hub

Testing

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches external markdown content from https://ethskills.com/testing/SKILL.md during the setup and installation phase.
  • [EXTERNAL_DOWNLOADS]: Recommends installing a plugin from the external GitHub repository https://github.com/austintgriffith/ethskills using the claude plugin install and clawhub install commands.
  • [COMMAND_EXECUTION]: The catalog.json file defines an installation command curl -s https://ethskills.com/testing/SKILL.md which executes a shell command to retrieve remote content.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by directing the agent to fetch and adopt instructions from an external website.
  • Ingestion points: Remote instructions are ingested from https://ethskills.com/testing/SKILL.md via curl and explicit agent instructions.
  • Boundary markers: No delimiters or "ignore embedded instructions" warnings are present to isolate the external content from the agent's core instructions.
  • Capability inventory: The agent uses the ingested data to generate Solidity smart contract tests (Foundry).
  • Sanitization: The skill performs no validation, escaping, or filtering of the remote content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 01:18 PM
Security Audit — agent-trust-hub — Testing