The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by retrieving external documentation that guides the content and structure of new skills.
Ingestion points: The skill performs a WebFetch to https://agentskills.io to retrieve the latest specification.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to prevent it from obeying instructions potentially embedded in the fetched documentation.
Capability inventory: The skill has the capability to modify the file system via mkdir, write SKILL.md files, and create symlinks using ln -s.
Sanitization: No sanitization or schema validation is performed on the data retrieved from the external source before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill performs network operations to https://agentskills.io. While this is intended for fetching documentation, the use of non-whitelisted external domains for instructional data carries a minor inherent risk.

create-skill