backlog-grooming-assistant

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE] (SAFE): No malicious patterns, obfuscation, or data exfiltration attempts were detected in the skill file. The content is restricted to documentation and metadata.
  • [Indirect Prompt Injection] (LOW): The skill presents an attack surface for indirect prompt injection as it is designed to process external backlog data while having access to powerful tools like Bash. 1. Ingestion points: User-provided backlog items and enterprise workflow requests. 2. Boundary markers: Absent. 3. Capability inventory: Bash, Read, Write, Edit (as declared in allowed-tools). 4. Sanitization: Absent in the documentation provided.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:30 PM