ghl
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on a pre-installed local binary located at
/opt/hatch/bin/ghlto interact with the HighLevel API. It executes various subcommands such asstatus,list-operations,call-tool, andexecute-operationto perform its tasks. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and process untrusted external data, such as customer messages, contact notes, and form submissions from the HighLevel CRM.
- Ingestion points: Data is ingested via the
/opt/hatch/bin/ghl execute-operationcommand when performing read operations on CRM, messaging, and calendar domains. - Boundary markers: The provided instructions do not specify any delimiters or special handling to differentiate between system instructions and data retrieved from external API responses.
- Capability inventory: The skill possesses significant capabilities, including the ability to create, update, and delete CRM records, send or cancel messages, and manage automation enrollments (workflows/campaigns).
- Sanitization: There is no evidence of sanitization, filtering, or escaping of retrieved external content before it is processed by the agent.
Audit Metadata