The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown documentation and YAML configuration files. There are no scripts, binaries, or command-line executions present in the skill package. All instructions are focused on providing a design framework for sponsorship packages.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided data about creator capacity and campaign goals. While this constitutes an ingestion surface for indirect prompt injection, the skill does not possess any capabilities (such as tool invocation, file system access, or network requests) that could be exploited by such an injection.
[METADATA_POISONING]: All metadata fields in the SKILL.md and agents/openai.yaml files are accurate and descriptive. They align perfectly with the skill's actual behavior and do not contain any hidden instructions or deceptive patterns.

sponsorship-package