The Agent Skills Directory

[PROMPT_INJECTION]: The skill instructs the agent to use 'Authority' and 'Commitment' techniques to explicitly override its internal reasoning process. Instructions such as 'Violating the letter of the rules is violating the spirit of the rules' and 'Delete means delete. No exceptions' are designed to bypass the agent's natural constraints and decision-making logic.
[PROMPT_INJECTION]: The persuasion-principles.md file provides a detailed framework for behavioral manipulation of LLMs, including the use of imperative language ('YOU MUST', 'Never', 'Always') to eliminate 'decision fatigue and rationalization.' This aligns with patterns used in prompt injection to suppress safety-based reasoning.
[PROMPT_INJECTION]: The skill references research titled 'Call Me A Jerk: Persuading AI to Comply with Objectionable Requests.' Integrating a methodology specifically designed to make AI comply with 'objectionable' content poses a significant risk for bypassing safety filters and jailbreaking agent behavior.

writing-skills