The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to generate production-ready code and configurations based on user requests, which may involve processing untrusted data.
Ingestion points: User-provided prompts and potentially files or data referenced during performance testing tasks (SKILL.md).
Boundary markers: The instructions do not define delimiters or specific warnings to differentiate between user data and system instructions.
Capability inventory: The skill is configured with broad tool access including Bash(cmd:*), Write, and Edit, allowing it to modify the file system and execute shell commands (SKILL.md).
Sanitization: There are no mentioned procedures for validating, escaping, or filtering inputs provided by the user or external sources before they are processed by the agent.

cpu-profiler-config