skills/aave/skills/deleverage/Gen Agent Trust Hub

deleverage

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes dynamic data ingested from the Aave protocol to generate recommendations and simulations.
  • Ingestion points: External data is ingested through tools including get_user_summary, get_user_positions, get_markets, and get_repay_with_supply_quote (SKILL.md).
  • Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious content embedded in the protocol data.
  • Capability inventory: The skill uses the preview_action tool to simulate transactions and performs internal calculations to recommend financial routes.
  • Sanitization: There is no explicit logic for filtering or sanitizing strings returned from the Aave protocol tools before they are used in the decision-making process.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 01:24 PM
Security Audit — agent-trust-hub — deleverage