exif_metadata_analyzer

Warn

Audited by Snyk on Mar 4, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly instructs the agent to load and analyze EXIF from arbitrary image_bytes (user/uploaded images), reading untrusted user-generated metadata and using it to set antifraud flags (e.g., add EXIF_EDITING_SOFTWARE), so third-party EXIF content can materially influence agent decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 12:24 AM