spree-headless-storefront
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches project documentation and clones the official storefront repository from Spree's GitHub organization (spree/storefront). These references target well-known and established sources for the platform's ecosystem.
- [COMMAND_EXECUTION]: Instructs the agent to execute standard development commands, such as
git cloneandnpm install, which are necessary for the skill's primary purpose of setting up a storefront environment. - [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection through the ingestion of external data.
- Ingestion points: The agent is directed to fetch live documentation from
github.comandspreecommerce.orgin theSKILL.mdfile. - Boundary markers: No explicit delimiters or "ignore embedded instructions" warnings are provided for the content fetched from these external URLs.
- Capability inventory: The skill has access to shell commands (
Bash), file manipulation (Write,Edit), and network fetching tools. - Sanitization: The skill does not define a process for sanitizing or validating the documentation fetched before it is processed by the agent.
Audit Metadata