cekura-create-agent
Use when the user asks to "create a main agent", "set up a main agent", "add my main agent to Cekura", "configure my main agent", "connect my main agent", "set up mock tools", "add tools to my agent", "upload knowledge base", "configure integration", "connect VAPI", "connect Retell", "connect LiveKit", "connect ElevenLabs", "add dynamic variables", or needs to onboard a voice AI agent onto the Cekura platform. Covers the full agent setup flow: project selection, provider selection, basics and connection type, description, main agent creation, mock tools, knowledge base, dynamic variables, and advanced configuration.
67
—
Does it follow best practices?
Impact
—
No eval scenarios have been run
Risky
Do not use without reviewing
Security
3 findings — 1 high severity, 2 medium severity. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
Insecure credential handling detected (high risk: 0.90). The prompt requires collecting provider API credentials up front and explicitly shows auth headers (X-CEKURA-API-KEY: <key>) and fallback curl/script usage, which can force the agent to place secret values verbatim into generated requests or commands.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
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.
Why it was flagged
Third-party content exposure detected (medium risk: 0.65). Phase 11 runs end-to-end scenarios and inspects `transcript_object` from the scenario result; that transcript is agent/user message text produced during the run (i.e., outsider-authored free text from the testing scenario’s “user” side) and is fed back into the agent’s LLM context for decision-making on success/failure.
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs runtime fetching and execution of external code and prompt content — e.g., cloning and running the WebSocket server example from https://github.com/cekura-ai/llm-websocket-server-example, calling provider APIs to import system prompts such as https://api.vapi.ai/assistant/{assistant_id}, https://api.retellai.com/get-agent/{agent_id}, https://api.elevenlabs.io/v1/convai/agents/{agent_id}, and using the mock-tool endpoint https://api.cekura.ai/test_framework/v1/aiagents/{agent_id}/tool/{tool_name}/ at runtime to drive agent behavior — all of which meet the criteria for external runtime dependencies that directly control prompts or execute code.
- Repository
- cekura-ai/cekura-skills
- Commit
f0854af
- Audited
- Security analysis
Is this your skill?
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.