Skills
skills/kwazema/claude-skills/kw-gsd-help-flow/Gen Agent Trust Hub

kw-gsd-help-flow

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely informational and does not define any tools (allowed-tools is absent). It functions as a lookup table and logic guide for the AI to help users navigate the GSD pipeline.
  • [EXTERNAL_DOWNLOADS]: The documentation references the official GSD repository on GitHub and an installation command for the author's NPM package. These are standard informational links and dependencies related to the skill's purpose.
  • [PROMPT_INJECTION]: The skill processes untrusted user input (task descriptions) to suggest workflows in SKILL.md.
  • Ingestion points: User-provided task arguments processed by the analysis logic.
  • Boundary markers: Absent.
  • Capability inventory: None; the skill has no tool access or executable scripts.
  • Sanitization: Absent.
  • Since the skill has no automated capabilities and only produces text suggestions for human review, the risk of indirect prompt injection is negligible.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 08:04 PM