deepread-insurance
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill integrates with the vendor's official API at
api.deepread.techfor document processing and PII redaction. - [SAFE]: Secret management instructions follow best practices, advising users to store API keys in environment variables rather than hardcoding them.
- [SAFE]: File operations are limited to reading the input document (
claim.pdf) and writing the redacted output (claim_redacted.pdf), which is consistent with the skill's stated purpose. - [SAFE]: All external references target the vendor's official domains, GitHub repositories, or well-known package registries (NPM).
- [SAFE]: No patterns of prompt injection, obfuscation, or malicious command execution were detected.
Audit Metadata