strk20-wallet-api

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to recommend the installation of libraries from the Starknet ecosystem, specifically starknet, @starknet-io/get-starknet-discovery, @starknet-io/get-starknet-wallet-standard, @starknet-io/types-js, and @avnu/avnu-sdk. It also refers users to external repositories and live demos for testing and implementation.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines patterns for the agent to process data originating from user wallets, which represents a potential ingestion surface for external content.
  • Ingestion points: Data is retrieved via API calls such as supportedWalletApi and strk20Balances.
  • Boundary markers: The skill does not specify particular markers or delimiters for the data returned by these API calls.
  • Capability inventory: The skill is strictly documentation-based and does not include any scripts that execute in the host environment; its instructions involve constructing calldata for wallet-side execution.
  • Sanitization: The skill explicitly advocates for secure development practices, including transaction simulation, address normalization, and the exclusion of private viewing keys from the application layer.
  • [NO_CODE]: The skill contains only Markdown documentation and YAML configuration files, with no bundled executable scripts or logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 06:50 AM
Security Audit — agent-trust-hub — strk20-wallet-api