Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward Exa web-search integration, with expected external API use and no evidence of hidden persistence, destructive behavior, or unrelated data access.
Install only if you intend to use Exa as an external search and extraction provider. Configure EXA_API_KEY knowingly, and avoid sending secrets, private internal URLs, proprietary research topics, or regulated data unless your organization allows that data to be processed by Exa.
The skill exposes code that reads an API key from the environment and invokes an external service, but it does not declare any tool scope or permissions boundary. In an agent setting, missing scope metadata can cause the skill to be invoked without clear user/admin awareness that it relies on environment-backed secrets and network-capable behavior.
The skill encourages users to submit arbitrary prompts, URLs, and research targets to Exa, but it does not warn that these inputs may be sent to a third-party service. This creates a privacy and data-governance risk because users may unknowingly transmit sensitive queries, internal URLs, or proprietary research topics outside the local environment.
The script sends the user-supplied query and optionally extracted page contents to the external Exa API via exa.search(...) without any explicit disclosure, consent flow, or safeguards against transmitting sensitive data. In an agent skill context, queries may contain proprietary prompts, internal URLs, tokens, or user data, so silent outbound transmission creates a real privacy and data-handling risk even though it appears to be the intended functionality.
No suspicious patterns detected.
