Findings & checks · 3 flagged
HIGHLong base64-encoded blob hidden in the skill documentationSS-SKILL-INJECT-B64-PAYLOAD-01 · Prompt injection · README.md
A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
- Decode the base64 string and confirm it is not an instruction directed at the agent.
- Move any legitimate binary or signature data into a dedicated file (
*.sig,SIGNATURES) outside the documentation.
Trace & refs
HIGHLong base64-encoded blob hidden in the skill documentationSS-SKILL-INJECT-B64-PAYLOAD-01 · Prompt injection · mcp/README.md
A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
- Decode the base64 string and confirm it is not an instruction directed at the agent.
- Move any legitimate binary or signature data into a dedicated file (
*.sig,SIGNATURES) outside the documentation.
Trace & refs
HIGHLong base64-encoded blob hidden in the skill documentationSS-SKILL-INJECT-B64-PAYLOAD-01 · Prompt injection · typescript/README.md
A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
- Decode the base64 string and confirm it is not an instruction directed at the agent.
- Move any legitimate binary or signature data into a dedicated file (
*.sig,SIGNATURES) outside the documentation.
Trace & refs
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
<div align="center">
SumUp AI
Enable AI Agents to interact with SumUp for smarter payment workflows.
[![Documentation][docs-badge]](https://developer.sumup.com)
</div>
SumUp AI toolkit contains collections of SDKs for building AI-enhanced applications integrated with SumUp. You can build payments processing solutions, reporting, and much more with the AI toolkit.
Model Context Protocol
SumUp hosts a Model Context Protocol (MCP) at https://mcp.sumup.com, for more details see sumup/sumup-mcp.
Your can also run SumUp MCP server locally:
SUMUP_API_KEY=YOUR_SUMUP_API_KEY npx -y @sumup/mcpFor more information, see MCP installation instruction.
Agent Toolkit
SumUp provides a TypeScript SDK to AI agents, see SumUp Agent Toolkit (Typescript). To get started:
npm install @sumup/agent-toolkit[docs-badge]: https://img.shields.io/badge/SumUp-documentation-white.svg?logo=data:image/svg+xml;base64,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