The Agent Skills Directory

[PROMPT_INJECTION]: The skill provides instructions to modify the agent's communication style using ASD-STE100 Simplified Technical English. These instructions are consistent with the skill's stated purpose of clarifying information and do not attempt to bypass safety filters or extract system prompts.
[DATA_EXPOSURE]: The skill references a local CONTEXT.md file for project-specific terminology, which is standard behavior for maintaining consistency. There is no evidence of sensitive data harvesting or exfiltration.
[REMOTE_CODE_EXECUTION]: No external dependencies, scripts, or remote code execution patterns were detected. The skill configuration explicitly disables model invocation, preventing the agent from calling external tools while this skill is active.

wait-what