Skills
skills/nmalinowski/groundwork/next-task/Gen Agent Trust Hub

next-task

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data access detected.
  • [PROMPT_INJECTION]: The skill parses local files in specs/tasks.md and specs/tasks/ to manage workflow. This creates a surface for indirect prompt injection. 1. Ingestion points: specs/tasks.md and specs/tasks/. 2. Boundary markers: Absent. 3. Capability inventory: Invokes groundwork:execute-task. 4. Sanitization: Absent.
  • [COMMAND_EXECUTION]: The skill uses the internal Skill tool to delegate tasks to groundwork:execute-task, which is a legitimate architectural pattern for workflow orchestration.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 09:41 PM