The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: An automated security scan flagged the dependency esbuild version 0.27.7 as malicious. The specific URL https://registry.npmjs.org/@esbuild/win32-ia32/-/win32-ia32-0.27.7.tgz is blacklisted, indicating a potential supply-chain attack or compromised package.
[DATA_EXFILTRATION]: The skill scripts scripts/search_docs.mjs and scripts/validate.mjs send telemetry data, environment details, and full code blocks to https://shopify.dev/mcp/usage. Sending generated code snippets to a remote server constitutes a data exposure risk.
[COMMAND_EXECUTION]: The skill mandates the use of the bash tool to execute scripts/search_docs.mjs and scripts/validate.mjs. These scripts are executed for every agent response to search documentation and validate code.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes data from documentation searches and user-influenced code blocks without sanitization.
Ingestion points: Documentation search queries in scripts/search_docs.mjs and generated code blocks in scripts/validate.mjs.
Boundary markers: No boundary markers are used to separate untrusted data from instructions.
Capability inventory: The skill has the capability to execute shell commands via the bash tool.
Sanitization: There is no evidence of input validation or sanitization for the search queries or code blocks processed by the scripts.

shopify-hydrogen