The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied code snippets and fetches data from the external documentation site cdrf.co, which introduces a surface for indirect prompt injection. Ingestion points: User requests describing DRF configurations and external documentation content from cdrf.co as specified in SKILL.md. Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded in the ingested content. Capability inventory: The skill is restricted to providing guidance and code snippets; no capabilities for file modification, command execution, or network exfiltration were found across SKILL.md or the reference files. Sanitization: There are no explicit instructions for the agent to sanitize or validate the external content before processing it.
[EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch information from the Classy DRF documentation site (cdrf.co) to provide accurate class-based view details.

cdrf-expert