USDD / JUST Protocol

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from the TRON blockchain, an external and untrusted source, which presents a surface for indirect prompt injection.
  • Ingestion points: Data ingestion occurs through blockchain queries in balance.js, psm-info.js, psm-swap.js, and vault-info.js.
  • Boundary markers: No explicit delimiters are used in the prompt context to segregate data retrieved from the network.
  • Capability inventory: The skill can perform sensitive actions such as token approvals and contract swaps as defined in psm-swap.js.
  • Sanitization: Standard data normalization is performed, but no specific adversarial filtering of string-based blockchain data is implemented.
  • [SAFE]: The skill follows secure practices by using environment variables for the TRON private key instead of hardcoding. It interacts with legitimate protocol contracts and uses the established tronweb library for network communication.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 10:05 PM
Security Audit — agent-trust-hub — USDD / JUST Protocol