spree-typescript-sdk
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch live documentation from external sources to inform its actions, which introduces a potential attack surface if those sources are compromised.
- Ingestion points: External data is fetched from
spreecommerce.organdgithub.com/spree/sdk(SKILL.md). - Boundary markers: There are no explicit instructions or delimiters provided to the agent to treat fetched content as untrusted or to ignore embedded instructions.
- Capability inventory: The skill possesses
WebFetchfor data ingestion andBash,Write, andEdittools that could be influenced by malicious content in the documentation. - Sanitization: No sanitization or validation steps are defined for the content retrieved from external URLs.
- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the
@spree/sdkpackage from the npm registry. This is a standard, well-known package for Spree Commerce development and is considered a safe dependency reference.
Audit Metadata