scrum-master

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands to run internal Python scripts (velocity_analyzer.py, sprint_health_scorer.py, and retrospective_analyzer.py) for sprint analysis. This functionality is the primary purpose of the skill.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external JSON data, creating a potential surface for instructions embedded in that data to influence the agent.\n
  • Ingestion points: sprint_data.json (referenced in SKILL.md).\n
  • Boundary markers: Absent from instructions.\n
  • Capability inventory: Authorized to execute shell commands to run analysis scripts.\n
  • Sanitization: No input sanitization or validation logic is specified in the agent's instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 08:06 PM
Security Audit — agent-trust-hub — scrum-master