exa-core-workflow-b
Execute Exa findSimilar, getContents, answer, and streaming answer workflows. Use when finding pages similar to a URL, retrieving content for known URLs, or getting AI-generated answers with citations. Trigger with phrases like "exa find similar", "exa get contents", "exa answer", "exa similarity search", "findSimilarAndContents".
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: 0.90). The SKILL.md explicitly calls exa.findSimilar/findSimilarAndContents, exa.getContents, exa.answer and exa.streamAnswer to fetch and crawl arbitrary public URLs and web search results (including livecrawl and subpage crawling), so untrusted third‑party content is ingested and can directly influence the agent's answers and actions.
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.getContents / exa.findSimilar / exa.answer at runtime to fetch arbitrary webpages (e.g., https://arxiv.org/abs/2401.00001 shown in the examples) and uses that fetched page content as context for AI-generated answers, meaning external URLs can directly influence the agent's prompts/output.
- 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.