agent-shopping-safe-checkout
pawel-cell/agent-shopping-safe-checkout
Drop-in safety instructions for AI agents that handle real-world web purchases and e-commerce checkouts.
Overview
This skill provides strict operational guardrails and workflows for AI agents tasked with buying items on real merchant websites. It establishes three independent security layers: isolated browser execution profiles to prevent credential leaks, strict payment isolation via merchant-locked or single-use virtual cards with strict spending caps, and a mandatory human-in-the-loop verification gate requiring an exact textual phrase before order submission.
Capabilities
- ▸Browser automation via CDP integration
- ▸Isolated Chrome user profile management
- ▸Virtual card spend-request generation
- ▸Pre-submit order verification and summary generation
- ▸Post-transaction cleanup and card freezing
Best for
Purchasing items online via an LLM agent, Managing recurring web purchases with spending limits, Safely automating e-commerce errands without exposing primary credit cards
Works with
実タスクにどれだけ役立つか(機能の豊富さ・用途の明確さ)。 — AIによるcapabilities/use-cases解析
実装・指示の品質。 — AIによるSKILL.md/README解析
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
ありふれたラッパーではない独自性。 — AIによる独自性判定
コミュニティの採用度。 — GitHub Stars/Forks(対数スケール)
対応AIエージェントの広さ。 — AIによる対応エージェント判定
ライセンス不明/制限あり(Red)のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
Implements defense-in-depth with browser profile isolation, spending caps, merchant locks, and strict human verification gates to prevent unauthorized charges and prompt injection vulnerabilities during e-commerce operations.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.