revops-hubspot
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill architecture is designed to ingest and process untrusted external data from leads and companies. 1. Ingestion points: Contact and company records populated from external forms or enrichment integrations (as described in references/hubspot-workflow-recipes-ready-to-implement.md). 2. Boundary markers: Absent; there are no instructions to use delimiters or warnings to ignore instructions within the ingested data. 3. Capability inventory: Restricted to CRM internal actions such as stage transitions, task creation, and Slack notifications. 4. Sanitization: Absent; no filtering or validation logic is defined for data processed within the workflows.
- [NO_CODE]: The skill does not contain any executable scripts, binary files, or command-line instructions. It is composed entirely of markdown documentation and design patterns.
Audit Metadata