skills/bankrbot/moltbot-skills/hydrex/Gen Agent Trust Hub

hydrex

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches dynamic strategy data and Merkle proofs from official subdomains including api.hydrex.fi and incentives-api.hydrex.fi. These downloads are essential for providing up-to-date protocol information and enabling users to claim rewards.
  • [PROMPT_INJECTION]: The skill processes data from external protocol APIs, which constitutes a vulnerability surface for indirect prompt injection. 1. Ingestion points: The skill retrieves pool metadata and reward proofs from hydrex.fi API endpoints. 2. Boundary markers: The prompt templates lack explicit delimiters or instructions to ignore potential commands embedded in the fetched data. 3. Capability inventory: The agent has access to the bankr tool, which can execute financial transactions on the Base network. 4. Sanitization: No explicit logic is provided to validate or sanitize the API responses before they are used to influence agent decisions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 02:43 AM