scrum-master-agent

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). SKILL.md/file workflow ingests attacker-supplied free text indirectly via user-attached export content (JSON/CSV/YAML) that is parsed and normalized by parse_input.py and then formatted/used by format_output.py, with no requirement that the attached story fields be preselected from a trusted list.