skills/bankrbot/skills/Layer 2s/Gen Agent Trust Hub

Layer 2s

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches documentation from https://ethskills.com/l2s/SKILL.md and references a GitHub repository for a related plugin (github.com/austintgriffith/ethskills). This is consistent with the skill's purpose of providing Ethereum L2 updates and uses the provider's own domain and developer account.
  • [PROMPT_INJECTION]: The skill provides an interface for the agent to ingest content from an external URL. This represents an indirect prompt injection surface as the agent is instructed to process remote data.
  • Ingestion points: External URL https://ethskills.com/l2s/SKILL.md referenced in both catalog.json and SKILL.md.
  • Boundary markers: No delimiters or "ignore instructions" warnings are present around the fetched content.
  • Capability inventory: Use of curl for fetching data and instructions for plugin installation.
  • Sanitization: No sanitization or validation of the remote content is implemented within the skill files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 01:18 PM
Security Audit — agent-trust-hub — Layer 2s