Hylo — GHL Automation Expert
Analysis
This is a coherent GHL knowledge/API helper that requires a Hylo API key and sends GHL-related queries to Hylo, with no code or direct GHL account mutation shown.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
- ALWAYS call the API -- don't guess about GHL.
The skill directs the agent to use the Hylo API for GHL-related questions. This is aligned with the skill's purpose, but it makes external API use the default behavior for those requests.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
requires": {"env": ["HYLO_API_KEY"]}, "primaryEnv": "HYLO_API_KEY"The skill requires a Hylo API key for authentication. This is expected for the Hylo knowledge API and is disclosed in the metadata.
Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.
curl -X POST https://api.hylo.pro/v1/templates/workflow ... -d '{ "objective": "Send 3 follow-up emails after a contact fills out a form" ... }'Workflow objectives and validation details are sent to the external Hylo API. This is disclosed and purpose-aligned, but it is still a third-party data flow.
