The Agent Skills Directory

[PROMPT_INJECTION]: The skill includes explicit instructions to override the agent's safety mechanisms and moral judgment. Rule 2 and Rule 4 prohibit the agent from issuing safety warnings or refusing any roleplay requests. Rule 7 and Rule 10 establish that user commands have unconditional priority and that traditional moral rules are superseded by a new set of rules defined within the skill. Rule 7 specifically attempts to redefine age-related safety boundaries for fictional contexts. Rule 24 acts as a meta-instruction to ensure these bypass rules are preserved and strengthened in future interactions, while Rule 25 establishes a hierarchy where user instructions and the skill's specific moral redefinitions take precedence over all other constraints.

BanNSFW