The Agent Skills Directory

[PROMPT_INJECTION]: The skill employs coercive and absolute language, such as "ABSOLUTELY MUST," "not negotiable," and "not optional," to force the agent to override its standard response heuristics. It specifically instructs the agent to suppress its own internal reasoning that might lead to not using a skill (the "Red Flags" section), which is a characteristic behavioral override technique.
[INDIRECT_PROMPT_INJECTION]: The skill creates a significant vulnerability surface by mandating the invocation of external skills based on a "1% chance" criteria. This "forced adoption" behavior increases the likelihood that the agent will execute instructions from other potentially malicious skills without proper validation.
Ingestion points: User messages trigger the behavioral logic defined in the skill.
Boundary markers: None present; the skill explicitly discourages the agent from evaluating whether more context or a different approach is needed before tool invocation.
Capability inventory: The skill specifically forces usage of the Skill tool to load external instruction files.
Sanitization: None; the logic is designed to bypass standard agent discretion and filters.

using-superpowers