| name | ingest-markdown-report |
| description | Submit a security report to Pi as inline Markdown with a .md or .markdown filename, after explicit user confirmation. Reports the queued ingestion workflow state truthfully. |
Submit a Markdown security report to Pi
Use this skill only when the user explicitly asks to submit or ingest a security report into Pi Security, and the report content is available inline as Markdown.
Tool
State-changing, confirmation required:
pi_report_markdown_upload - uploads Markdown report content and starts the tenant report-ingestion workflow. Inputs: fileName (must end in .md or .markdown) and content (non-empty Markdown, up to 5 MiB).
Accepted input
Report content provided inline in the conversation as Markdown, plus a filename ending in .md or .markdown. If either is missing, ask for it instead of inventing one.
Rejected inputs
- Chat attachments, local file paths, and
file:// URIs
- PDFs, DOCX files, images, or any binary content
Those workflows belong in the Pi web app or the Sloane CLI, not this skill.
Before calling the tool
- Validate:
fileName ends in .md or .markdown, and content is non-empty Markdown within the size limit.
- Summarize what will be submitted - filename, approximate size, and a one-line description of the report's scope. Do not echo sensitive report content back into the conversation beyond what is needed to confirm the target.
- Explain the effect: Pi will store the report and start its ingestion workflow in the authenticated tenant.
- Ask for confirmation and proceed only on an explicit yes in the current turn.
- Call the tool once.
- Report exactly the upload and workflow state Pi returned. Queued or started means ingestion is in progress, not that findings exist yet. Never invent ingestion results.
- If the call fails or times out ambiguously, report that and stop. Do not retry automatically, since a retry could submit a duplicate report.
