The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from inbound discovery-call emails without implementing sanitization or boundary markers.
Ingestion points: The skill searches for and fetches Gmail message bodies from website@zynkr.ai (SKILL.md, Workflow Step 1 and 2).
Boundary markers: There are no explicit delimiters or "ignore embedded instructions" warnings used when processing the Brief context field.
Capability inventory: The skill possesses the ability to write to a CRM via mcp__zynkr__create_deal and mcp__zynkr__update_deal, as well as create and modify Google Drive files and folders via mcp__google-workspace__create_drive_file, create_doc, and update_drive_file (SKILL.md, Workflow Step 4).
Sanitization: The Brief context text is directly interpolated into the CRM deal notes and a Google Doc kickoff template using the {{CONTEXT}} and {{NOTES}} placeholders without any validation or filtering (SKILL.md, Workflow Step 4a and 4c).

consult-intake