scp-elementkg-2

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt shows and instructs embedding an API key directly into request headers and example code (e.g., "SCP-HUB-API-KEY": "{API-KEY}" and "sk-xxx"), which would require the model to include secret values verbatim in generated outputs.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow calls the MCP tool get_experiment_workflow on a remote server (https://scp.intern-ai.org.cn/.../SciGraph), and the tool’s returned “full workflow of an ElementKG experiment” is outsider-authored free text/data from that external knowledge graph that is ingested into the agent’s LLM context.