video-wrapper
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill directly reads user-supplied/open subtitle files (src/content_analyzer.py: parse_srt) and inserts that untrusted subtitle text into the ANALYSIS_PROMPT (see src/content_analyzer.py) for AI analysis, so arbitrary third-party content is ingested and interpreted as part of the workflow.
Audit Metadata