exa-reference-architecture
Implement Exa reference architecture for search pipelines, RAG, and content discovery. Use when designing new Exa integrations, reviewing project structure, or establishing architecture standards for neural search applications. Trigger with phrases like "exa architecture", "exa project structure", "exa RAG pipeline", "exa reference design", "exa search pipeline".
76
—
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Security
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: 1.00). The skill clearly ingests untrusted public web content via Exa API calls (e.g., exa.searchAndContents and exa.findSimilarAndContents in Step 1: src/exa/service.ts) and then uses results.results[].text and URLs to build LLM context and drive decisions (see Step 3: src/exa/rag.ts where content from arbitrary domains like GitHub/StackOverflow/news sites is injected into the agent's context), so third‑party content can materially influence behavior.
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 calls the Exa API (api.exa.ai) at runtime via exa.searchAndContents / findSimilarAndContents to fetch external page contents which are directly injected into LLM context/prompts, so api.exa.ai is a runtime dependency that can control prompts.
- Commit
02d6341
- 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.