prioritize

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements standard prioritization logic for project management tasks, such as scoring and ranking backlog items.
  • [DATA_EXFILTRATION]: No sensitive file access or network communication was observed. The skill operates on local project artifacts (e.g., team-artifacts/pbis/) as part of its documented purpose.
  • [PROMPT_INJECTION]: The instructions provide a structured workflow for the agent without attempting to bypass safety guidelines or override core behavior. The directive to use TaskCreate is a task-management preference rather than a malicious override.
  • [SAFE]: The skill ingests data from backlog files and user input. While it has access to file-writing and bash tools, there is no evidence of unsafe interpolation or instructions to execute external content. (Ingestion points: team-artifacts/pbis/ and user messages; Boundary markers: Not explicitly defined; Capability inventory: Read, Write, Edit, Bash; Sanitization: Not explicitly mentioned).
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 08:32 PM