extract-source-sample

Warn

Audited by Snyk on Jul 2, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.85). The skill reads outsider-authored free text from run-dir/HOW_TO_MAKE_THIS_VIDEO.md and dumps it verbatim into the LLM context as how_to, which is runtime ingestion of arbitrary markdown authored by someone other than the operating user.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 2, 2026, 06:16 AM
Issues
1
Security Audit — snyk — extract-source-sample