flow-nexus-neural
Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus
72
61%
Does it follow best practices?
Impact
96%
7.38xAverage score across 3 eval scenarios
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./skills/ai-ml/flow-nexus-neural-mattnigh-skills-collection/SKILL.mdLow
Low-risk findings.
2 low severity findings. Worth noting, but not necessarily harmful.
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
The SKILL.md explicitly includes a "Template Marketplace" workflow (mcp__flow-nexus__neural_list_templates, mcp__flow-nexus__neural_deploy_template and the https://flow-nexus.ruv.io/templates URL) that fetches and acts on public marketplace templates (likely user-contributed/untrusted) which the agent reads and can use to drive deployments and training, so third-party content could influence tool use.
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's prerequisites require running "npx flow-nexus@latest" (shown as "claude mcp add flow-nexus npx flow-nexus@latest mcp start" and "npx flow-nexus@latest register"), which at runtime fetches and executes remote npm package code (npm registry: https://registry.npmjs.org/flow-nexus) that the skill depends on, so it is a runtime external code execution dependency.
- Repository
- majiayu000/claude-skill-registry
- Commit
ef92666
- 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.