ows-branding-layer
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install several Node.js packages from the
@1shotapiscope (includingows-types,ows-wallet-utils,ows-signer-utils,ows-oid4, andows-signer) as well as theviemlibrary. These are the required core dependencies for implementing the OWS protocol. - [COMMAND_EXECUTION]: The instructions include standard development commands for environment setup, such as
npx skills addandnpm installfor package management. - [INDIRECT_PROMPT_INJECTION]: The skill suggests analyzing code from a local clone of the
open-walletrepository to guide the scaffolding process, which constitutes an ingestion surface for untrusted data. - Ingestion points: Local grepping of files in the
examples/general-walletdirectory of a cloned repository. - Boundary markers: No specific delimiters are mandated for the ingested code content.
- Capability inventory: The skill enables file system writes for scaffolding, package installation, and the registration of RPC handlers.
- Sanitization: The instructions promote the use of strictly typed constructors from
@1shotapi/ows-typesandzodfor RPC schema validation to ensure data integrity.
Audit Metadata