clip-finetune-recipes

Warn

Audited by Snyk on Jun 13, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.75). The required runtime workflow for training uses a streaming WebDataset loader over user-supplied shard URLs/patterns (e.g., create_webdataset_loader(shard_pattern="s3://.../{00000..01999}.tar")), which ingests outsider-authored free text from the txt fields inside those tar shards into the LLM context via the training/evaluation code paths that consume captions as strings.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 13, 2026, 10:04 AM
Issues
1
Security Audit — snyk — clip-finetune-recipes