synap

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly tells the agent to ask the user to paste their synap_... API key into the conversation and to run/export it (export SYNAP_API_KEY=synap_...), which requires the LLM to receive and could echo or include the secret verbatim — a direct secret-exfiltration risk.

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

• Potentially malicious external URL detected (high risk: 0.90). The hosted MCP endpoint https://synap-mcp.maximem.ai/mcp is a runtime remote service the skill instructs clients to connect to (and to fetch recall_context), and the content returned by that endpoint is injected into system prompts—i.e., external runtime-fetched data directly controls the agent's prompt/context.