exa-lead-gen
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill utilizes the
mcportertool to interact with the Exa deep search API. This behavior is transparently documented and aligns with the skill's primary purpose of lead generation. - [SAFE]: No sensitive data access or credential exposure was detected. The skill uses standard tool calls without hardcoded secrets.
- [SAFE]: The instructions do not contain prompt injection attempts or efforts to bypass agent safety guidelines. The guidance is focused on task execution and data structuring.
- [SAFE]: While the skill processes data from external web searches, it mitigates indirect prompt injection risks by enforcing
structuredOutput=trueand using strict JSON schemas for data ingestion. - [SAFE]: The workflow involves a Python-based CSV compiler for data processing, which is a common and legitimate pattern for agents handling search results and reporting.
Audit Metadata