exa-core-workflow-a
Execute Exa neural search with contents, date filters, and domain scoping. Use when building search features, implementing RAG context retrieval, or querying the web with semantic understanding. Trigger with phrases like "exa search", "exa neural search", "search with exa", "exa searchAndContents", "exa query".
84
82%
Does it follow best practices?
Impact
Pending
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's SKILL.md explicitly uses exa.searchAndContents (Step 2) and livecrawl (Step 5) to fetch full page text, highlights, and summaries from public web pages, tweets, and personal sites and then instructs the agent to read and use that content (e.g., RAG context retrieval example), which exposes it to untrusted third-party content that could inject instructions.
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: 0.80). The skill calls exa.searchAndContents which at runtime fetches external web pages and injects their text into RAG context (e.g., domains shown as examples: devblogs.microsoft.com and typescriptlang.org), so remote page content can directly control model prompts.
- Commit
3a2d27d
- 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.