sales-gohighlevel
Pass
Audited by Gen Agent Trust Hub on Aug 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides legitimate documentation and integration resources for the GoHighLevel CRM platform. It correctly utilizes official API endpoints and recommends secure practices such as using environment variables for credentials in code examples.
- [PROMPT_INJECTION]: The skill implements a self-referential learning mechanism that serves as an attack surface for indirect prompt injection.
- Ingestion points: The agent is instructed to read context from 'references/learnings.md' at the start of its workflow.
- Boundary markers: The skill lacks explicit instructions or delimiters to isolate or ignore potentially malicious content within the learnings file.
- Capability inventory: The agent has the capability to write to the same file ('references/learnings.md'), allowing it to modify its own future behavioral context.
- Sanitization: There are no verification or sanitization steps mentioned for data appended to the learning file.
Audit Metadata