cold-email
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and analyze untrusted external data which could potentially contain malicious instructions aimed at overriding the agent's behavior during email generation.\n
- Ingestion points: External research signals including LinkedIn posts, company news, funding announcements, and website changes (found in
SKILL.mdandreferences/personalization.md).\n - Boundary markers: The instructions do not specify any delimiters or boundary markers (such as XML tags or unique tokens) to distinguish between trusted system instructions and untrusted external data.\n
- Capability inventory: The skill enables the agent to generate outreach text and references integrations with email sending tools (e.g., Instantly, lemlist) and CRM systems for reply handling and triage.\n
- Sanitization: No sanitization or validation protocols are defined for the external content before it is processed by the model for personalization.
Audit Metadata