scrum-sage

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data such as sprint reports and backlog items, which presents a theoretical attack surface for indirect prompt injection.
  • Ingestion points: Processes user-provided text files and project data (SKILL.md).
  • Boundary markers: The prompt does not explicitly define delimiters to separate system instructions from analyzed data.
  • Capability inventory: The agent has access to Read, Write, Grep, Glob, and WebSearch tools.
  • Sanitization: No specific data sanitization or instruction-filtering logic is implemented in the skill description.
  • [SAFE]: The skill's primary function is coaching and facilitation. The instructions are transparent, follow agile principles, and do not contain hidden malicious commands or exfiltration patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 01:49 AM