write-to-ado
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests data from external markdown files, which presents a surface for potential indirect prompt injection. \n
- Ingestion points: Markdown files generated by the
/plannerskill or other processes. \n - Boundary markers: No explicit delimiters or 'ignore instructions' markers are defined for the ingested file content. \n
- Capability inventory: The skill uses an MCP server to create Features, User Stories, and Tasks within an Azure DevOps organization and project. \n
- Sanitization: The skill instructs the agent to manually verify the clarity of the plan and to stop execution if any ambiguities or missing information are detected.
Audit Metadata