The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's primary function is to discover and process content from untrusted external GitHub repositories, which creates a surface for indirect prompt injection.
Ingestion points: The agent is instructed to explore target repositories and extract metadata from arbitrary SKILL.md files (SKILL.md).
Boundary markers: The instructions do not specify the use of delimiters or "ignore embedded instructions" prompts when reading content from external sources.
Capability inventory: The skill utilizes repository exploration tools and performs local file-write operations to update the README.md catalog.
Sanitization: There are no explicit instructions to sanitize or validate the content extracted from external SKILL.md frontmatter before it is included in the local documentation.

skill-curator