The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute various system utilities, including codesign, PlistBuddy, pgrep, ps, and defaults. It also executes a locally resident binary, test_session, located in the plugin's build directory to gather test results.\n- [DYNAMIC_EXECUTION]: The skill includes instructions in the "Self-Evolving Skill" and "Post-Execution Reflection" sections that command the agent to rewrite the SKILL.md file itself to fix errors or artifact drift. This encourages self-modifying behavior where the skill's own logic can be changed by the AI at runtime.\n- [INDIRECT_PROMPT_INJECTION]: The diagnostic script ingests the output of the test_session binary and the ActiveProfile configuration value from the system defaults. This data is included in the agent's context without boundary markers or sanitization, creating a surface where external or previously modified data could influence the agent's behavior during the diagnostic process.\n
Ingestion points: Output of the test_session binary and the ActiveProfile value from defaults.\n
Boundary markers: No delimiters or instructions are used to separate external content from the skill's core logic.\n
Capability inventory: The skill utilizes the Bash tool, allowing for significant system interaction and file modification.\n
Sanitization: No sanitization or validation of the gathered diagnostic data is performed before it is processed by the agent.

diagnose