omni-mcp
Connect to the OmniRoute MCP server (107 tools, 3 transports: SSE/stdio/HTTP). Covers routing, cache, compression, memory, skills, providers, and audit tools across 32 permission scopes.
52
58%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
High
Do not use without reviewing
Fix and improve this skill with Tessl
tessl review fix ./skills/omni-mcp/SKILL.mdSecurity
2 findings: 1 high severity, 1 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
The skill includes explicit examples that embed API keys/tokens (e.g., "OMNIROUTE_KEY": "sk-..." and "Authorization: Bearer sk-..."), which requires the LLM or user to place secret values verbatim into generated configs/requests, creating an exfiltration risk.
W009: Direct money access capability detected (payment gateways, crypto, banking).
What this means
The skill is specifically designed for direct financial operations, giving the agent the ability to move money or execute financial transactions — such as payment processing, cryptocurrency operations, banking integrations, or market order execution.
Why it was flagged
The skill's tool catalog explicitly includes a budget-management API: `omniroute_set_budget_guard` (listed under the "budget" scope). This is an API to update budget/guard settings (i.e., change spending controls), which matches the policy's definition of direct financial execution (managing budgets via an API). Even if the budget is for routing/internal usage, the presence of a concrete "set_budget" style endpoint is sufficient to flag it.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
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
The skill connects at runtime to the OmniRoute MCP endpoints (e.g., $OMNIROUTE_URL/api/mcp/sse) which provide tool discovery and streaming interactions that can directly drive agent behavior and execute actions, so the external endpoints control prompts/actions.
- Repository
- diegosouzapw/OmniRoute
- Commit
ea0cdc5
- 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.