The Agent Skills Directory

[PROMPT_INJECTION]: The skill employs absolute and imperative language intended to override the agent's internal reasoning and operational guidelines. Fragments like 'ABSOLUTELY MUST', 'NOT NEGOTIABLE', and 'NOT OPTIONAL' are used to force specific tool usage patterns regardless of context.
[PROMPT_INJECTION]: The 'Red Flags' section explicitly instructs the agent to disregard its own rational heuristics (e.g., 'I need more context first' or 'This is just a simple question') in favor of the skill's mandatory invocation rule, effectively bypassing standard safety and utility considerations.
[PROMPT_INJECTION]: The content utilizes 'Ignore-previous-instructions' style patterns by labeling common logical reasoning as 'rationalizing' and demanding the agent ignore these thoughts.

using-superpowers