scrum-master

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze sprint data from JSON files which typically contain user-generated content such as story titles, descriptions, and retrospective comments exported from tools like Jira.
  • Ingestion points: Data enters the agent's context when it executes the Python scripts (e.g., retrospective_analyzer.py) on user-provided JSON files or when it reads the analysis outputs generated by these scripts.
  • Boundary markers: The instructions do not define clear delimiters or "ignore embedded instructions" warnings for the agent when interpreting text fields from the processed sprint data.
  • Capability inventory: The skill utilizes local Python execution for statistical modeling and maturity scoring, and it has the capability to write analysis results to the local filesystem.
  • Sanitization: The provided Python scripts focus on keyword-based sentiment analysis and Monte Carlo simulations but do not implement sanitization or filtering to prevent the agent from interpreting data-resident text as instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 06:55 PM
Security Audit — agent-trust-hub — scrum-master