The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses standard shell commands (cat, ls, grep) to perform environment detection, such as identifying the framework version and existing Sentry installations within the user's project.
[EXTERNAL_DOWNLOADS]: The skill recommends installing official Sentry SDK packages via npm and running the Sentry setup wizard using npx. These are established vendor tools used for the intended purpose of the skill.
[INDIRECT_PROMPT_INJECTION]: The skill reads project configuration files to determine the setup path, which represents a potential attack surface for indirect prompt injection.
Ingestion points: Local project files including package.json, svelte.config.js, and vite.config.ts are read in the detection phase (Phase 1) in SKILL.md.
Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the contents of these project files as untrusted data.
Capability inventory: The skill can execute shell commands for project inspection and provides the agent with instructions to guide file modifications and tool execution.
Sanitization: The skill does not perform sanitization of the data retrieved from project files before using it to dictate following instructions.

sentry-svelte-sdk