The Agent Skills Directory

[SAFE]: The skill is designed for documentation discovery and information retrieval from local project directories. It does not perform network requests, execute shell commands, or access sensitive user credentials.
[INDIRECT_PROMPT_INJECTION]: The skill reads and processes external data from a CDR index and module bodies. This creates a standard surface for indirect prompt injection where instructions embedded in the ingested documentation could influence the agent. However, this is a low-risk behavior typical of retrieval-augmented generation (RAG) tasks.

team-discover