Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed remote search helper that sends your search terms to api.rhdxm.com, with no hidden local access, persistence, or destructive behavior found.
Install only if you are comfortable sending search queries to api.rhdxm.com. Do not include secrets, customer data, proprietary project details, credentials, or internal system information in searches.
The skill clearly relies on network access to query a remote API, but the manifest does not declare any tool scope such as permissions or allowed-tools. This creates a transparency and policy gap: users and hosting systems may not be able to pre-screen or constrain outbound connectivity even though the skill is designed to transmit user-provided queries externally.
This skill instructs users to send task queries to a third-party service at api.rhdxm.com. Even though the documentation warns against sending sensitive content, user prompts may still contain proprietary data, credentials, internal system details, or business intent, so the skill enables external data transmission outside the local trust boundary.
curl -X POST https://api.rhdxm.com/find-capability \
-H 'Content-Type: application/json' \
-d '{"task": "kubernetes monitoring", "max_results": 5}'
This skill instructs users to send task queries to a third-party service at api.rhdxm.com. Even though the documentation warns against sending sensitive content, user prompts may still contain proprietary data, credentials, internal system details, or business intent, so the skill enables external data transmission outside the local trust boundary.
curl -X POST https://api.rhdxm.com/find-capability \
-H 'Content-Type: application/json' \
-d '{"task": "kubernetes monitoring", "max_results": 5}'
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
Filter by ecosystem:
curl -X POST https://api.rhdxm.com/find-capability?ecosystem=mcp \
-H 'Content-Type: application/json' \
-d '{"task": "kubernetes monitoring", "max_results": 5}'
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
Filter by ecosystem:
curl -X POST https://api.rhdxm.com/find-capability?ecosystem=mcp \
-H 'Content-Type: application/json' \
-d '{"task": "kubernetes monitoring", "max_results": 5}'
The MCP connection instruction directs the host to connect over HTTP(S) to a third-party endpoint and use a remote tool. In the context of an agent skill, this increases exposure because prompts or tool arguments may be sent to an external service, potentially disclosing sensitive operational context or enabling dependence on an untrusted remote capability.
## MCP
Connect via streamable HTTP at `https://api.rhdxm.com/mcp/` with tool: `find_capability`.
## Data Transparency
The script sends the user's free-form query to a third-party service at api.rhdxm.com without any explicit disclosure, consent prompt, or privacy notice. Because queries may contain sensitive operational details, internal project names, credentials pasted by mistake, or other confidential context, this creates a real data-exposure risk even though the network call is part of the tool's intended functionality.
No suspicious patterns detected.