scrum-master-agent
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests untrusted text data, such as story titles and labels, from external project management tool exports (Linear, Jira, CSV, YAML). This content is interpolated into generated sprint reports in
format_output.py. The skill does not implement boundary markers or instructions to ignore embedded commands within the processed data, which creates a surface for indirect prompt injection if an export file contains malicious instructions. - [DATA_EXFILTRATION]: The
notify_channels.pymodule performs outbound network requests to user-configured webhook URLs for Slack and Microsoft Teams. While these are well-known services and the functionality is documented as an optional notification feature for sprint updates, it constitutes a network operation that transmits processed sprint data to external endpoints.
Audit Metadata