personalization-at-scale
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process prospect data from external sources such as CSV files or pasted text, creating a surface for indirect prompt injection attacks.
- Ingestion points: The workflow in
SKILL.mdstarts by ingesting a prospect list containing names, titles, and companies. - Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious content within the prospect data.
- Capability inventory: The agent uses the data to generate personalized outreach emails and campaign deliverables.
- Sanitization: There are no explicit steps for sanitizing or validating the input data before processing.
Audit Metadata