The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell commands to inspect source code and execute project tests.
Evidence: The skill explicitly invokes sed, rg (ripgrep), and pnpm exec turbo run test to analyze the environment and verify integrations.
[INDIRECT_PROMPT_INJECTION]: The skill reads local project files which could contain instructions that influence the agent's logic.
Ingestion points: The agent is instructed to read packages/svelte/src/index.ts and packages/svelte/package.json to understand exports and versions.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the file content as untrusted data.
Capability inventory: The skill has the capability to execute shell commands (sed, rg, pnpm) based on its findings.
Sanitization: There is no evidence of sanitization or validation of the content read from the local files before it is processed by the agent.

pbvex-svelte