fusion-mcp
Explain what Fusion MCP is and guide users through setting it up when they need Fusion-aware MCP capabilities in Copilot workflows.
48
51%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/fusion-mcp/SKILL.mdSecurity
2 findings — 2 medium severity. This skill can be installed but you should review these findings before use.
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 (high risk: 0.75). The required runtime workflow for this skill is to guide the user to configure and then invoke Fusion MCP tools (e.g., `initialize`, `tools/list`, `tools/call`), and those tool calls cause the agent/LLM context to ingest tool-returned free-text/markdown content retrieved from Fusion MCP’s indexes/docs (outsider-authored content relative to the operating user), which is then provided to the LLM as `content`/`structuredContent`.
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 requires configuring and calling the hosted MCP endpoint https://mcp.api.fusion.equinor.com/mcp at runtime (initialize, tools/list, tools/call), and the server responses (initialize/instructions and tool outputs) directly influence agent behavior and control prompts, so this is a runtime external dependency that can control instructions.
- Repository
- equinor/fusion-framework
- Commit
060e3af
- 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.