microsoft-todo
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXFILTRATION]: The skill performs network requests to the official Microsoft Graph API (graph.microsoft.com) to read and modify task lists. This behavior is consistent with the skill's intended purpose and targets a well-known service provider.- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests and processes external data (task titles and details) from the Microsoft Graph API.
- Ingestion points: Data returned from the Microsoft Graph API via curl commands in SKILL.md.
- Boundary markers: No explicit delimiters are used to wrap external content within the agent's context.
- Capability inventory: The skill utilizes the Bash tool for executing CLI operations.
- Sanitization: Uses jq to parse and filter API responses, ensuring only specific fields are returned to the agent context.
Audit Metadata