resume-checkpoint

Warn

Audited by Snyk on Aug 13, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.30). The required workflow invokes resume-checkpoint and passes the user’s continuation text as --prompt to scripts/pull_checkpoint.py, which then reads prior checkpoint .md content from the checkpoint store and returns it (fenced) to the model as context.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 13, 2026, 12:28 PM
Issues
1
Security Audit — snyk — resume-checkpoint