The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown documentation providing business frameworks and persona instructions. No malicious patterns or security risks were identified.- [PROMPT_INJECTION]: No instructions were found that attempt to override system safety guidelines or extract internal prompts. The logic is focused on routing user queries to the appropriate topical expert persona.- [DATA_EXFILTRATION]: No network operations (curl, wget, fetch) or sensitive file access patterns are present. The skill does not handle or store credentials or secrets.- [REMOTE_CODE_EXECUTION]: There are no scripts, package installations, or remote code downloads. The skill is entirely data-driven via Markdown files.- [INDIRECT_PROMPT_INJECTION]: While the skill processes user input to select expert responses, it includes strict boundary instructions (e.g., "Answer in that expert's voice using only the substance in the files you loaded") to prevent external content from overriding the agent's behavior.

dojo-brian-chesky