The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions for the agent to follow when analyzing data provided by the user. No suspicious patterns were detected.
[NO_CODE]: The skill does not include any scripts, command-line executions, or external dependencies. It relies solely on the LLM's reasoning capabilities.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided assumptions and research data. While this creates a surface for indirect prompt injection, the skill lacks any dangerous capabilities (such as network access or shell execution) that could be exploited by malicious input.

prioritize-assumptions