you-finance

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to request and/or use the YDC_API_KEY and explicitly embed it into request headers/commands (e.g., Authorization: Bearer ${YDC_API_KEY} and X-API-Key: ${YDC_API_KEY}), which requires the LLM to handle and potentially output secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md requires querying an external “You.com Docs MCP server” (searchDocs) and/or falling back to fetching a canonical docs page; those remote, outsider-authored text results would be read by the agent’s LLM context at runtime as tool output (untrusted external data).

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly directs the agent at runtime to query the You.com Docs MCP and to use the MCP server endpoint as a fallback (https://you.com/docs/api-reference/finance-research/v1-finance_research and https://api.you.com/mcp?tools=you-finance), so content fetched from these URLs would directly control prompts/instructions and code-generation.