The Agent Skills Directory

[NO_CODE] (SAFE): The skill consists entirely of Markdown files providing instructions and examples for the LLM. There are no Python scripts, Node.js packages, or shell commands associated with this skill.
[DATA_EXFILTRATION] (SAFE): There are no network-capable tools (like curl or fetch) or file-reading operations defined in the skill, making data exfiltration impossible within this scope.
[PROMPT_INJECTION] (SAFE): The instructions are straightforward and do not attempt to bypass safety filters or override the agent's core personality.
[INDIRECT_PROMPT_INJECTION] (SAFE): While the skill ingests user-provided task lists via the $ARGUMENTS placeholder, the skill has no 'capabilities' (no file-write, no shell execution, no network access). Therefore, even if a user provides a malicious task string intended to trigger an action, there are no tools available for the agent to execute such a command.
Ingestion points: SKILL.md, commands/eisenhower.md, and commands/prioritize.md via $ARGUMENTS.
Boundary markers: None present.
Capability inventory: None detected; the skill is strictly text-transformation based.
Sanitization: None present.

eisenhower