The Agent Skills Directory

[SAFE]: The skill provides purely instructional content for the agent to use in a conversational context. No malicious patterns or security risks were detected in the instructions or metadata.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied lists of features or initiatives. While these inputs are untrusted data, the skill does not possess any capabilities (such as shell execution, file writing, or network requests) that could be exploited through injection. The risk is limited to the agent's reasoning within the current session, and the skill includes clarification steps that help verify inputs.

prioritization-matrix