skills/simota/agent-skills/sherpa/Gen Agent Trust Hub

sherpa

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and research from well-known technology organizations and services, including GitHub (github.com/github/spec-kit), Linear (linear.app), Anthropic (claude.com), and DORA (dora.dev). These references provide context for the skill's planning and estimation framework and do not involve remote code execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input in the form of task descriptions and epics (SKILL.md, reference/task-breakdown.md). It manages this risk through a rigorous 'Decomposition Decision Gate' and an 'INVEST' quality checklist (reference/atomic-step-decomposition.md, reference/task-decomposition-anti-patterns.md) to ensure tasks are small and testable. The skill lacks dangerous execution capabilities, such as direct shell access or network operations across all analyzed files, effectively mitigating potential injection risks.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 01:06 PM