personalization-at-scale
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill provides markdown-based instructions for the AI agent to follow. It does not include any scripts, binaries, or command-line executions.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process prospect lists (CSV/manual input) which represent a potential entry point for indirect prompt injection.
- Ingestion points: Data is ingested through CSV or list uploads as defined in 'Step 1: Upload Prospect List'.
- Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious commands within the prospect data.
- Capability inventory: The skill is limited to text generation and research analysis. There are no subprocess calls, file-write operations, or network exfiltration capabilities defined within the skill's own instructions.
- Sanitization: No validation or sanitization of the input prospect data is specified.
- [SAFE]: No credentials, obfuscation, persistence mechanisms, or unauthorized privilege escalation attempts were detected. All external references are to well-known professional platforms such as LinkedIn and Crunchbase.
Audit Metadata