Composio Claude Agents SDK - 全局外部应用连接插件
58
36%
Does it follow best practices?
Impact
100%
3.33xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.trae/skills/connect-apps-plugin/SKILL.mdSecurity
2 findings — 2 medium severity. This skill can be installed but you should review these findings before use.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Third-party content exposure detected (high risk: 0.80). This skill's SKILL.md explicitly connects agents to third‑party services (e.g., Gmail, GitHub, Slack, Notion) via session.authorize/session.tools and OAuth flows and shows agent workflows (e.g., pushing updates to GitHub, reading/writing Notion, sending emails/Slack messages) that involve ingesting user-generated/untrusted content which can materially influence subsequent tool actions (notably with permission modes like bypassPermissions).
The skill is specifically designed for direct financial operations, giving the agent the ability to move money or execute financial transactions — such as payment processing, cryptocurrency operations, banking integrations, or market order execution.
Direct money access detected (high risk: 1.00). The skill explicitly lists Stripe under supported applications ("支付 | Stripe") and provides a generic connector/authorization flow (session.authorize, OAuth callbacks, session.tools(toolkits=...)) that would allow an agent to obtain and use Stripe credentials. Although the plugin is a general external-app connector, the presence of a specific payment gateway integration (Stripe) constitutes explicit capability to perform payment-related operations via that API, which meets the "Direct Financial Execution" criteria.
3069d33
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.