clay-toolkit
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The toolkit defines workflows that ingest external contact and company data which is subsequently processed by AI models.
- Ingestion points: Data enters the workflow via input columns defined in
SKILL.mdandreferences/gtm-table-blueprints.md, sourced from CSVs, Google Sheets, or APIs. - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat this ingested data as untrusted or to ignore instructions embedded within it.
- Capability inventory: The skill utilizes AI personalization columns (
ai_signal_line,ai_email_draft) and performs automated actions such as CRM pushes and webhook triggers based on the processed data. - Sanitization: The provided blueprints and templates do not include steps for sanitizing or validating lead data to prevent it from influencing the AI prompts or resulting in malicious CRM updates.
Audit Metadata