skills/proof-stamp/ai/proofstamp/Gen Agent Trust Hub

proofstamp

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a robust integrity and privacy model for session archiving. It uses local hashing (SHA-256) to ensure that exported JSON files are not altered. The bundled Python scripts (create_receipt.py, verify_proofstamp.py, and create_mailto.py) perform legitimate tasks like hashing local files twice for verification and generating pre-filled email templates for user-initiated sharing. All external references point to the vendor's own verification site (proofstamp.org) or use standard mailto protocols. No evidence of data exfiltration, credential theft, or prompt injection was found; the instructions explicitly warn the AI against capturing sensitive data like credentials or bypassing system prompt protections.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 04:20 PM
Security Audit — agent-trust-hub — proofstamp