khe-brain-enrico

Warn

Audited by Snyk on Nov 17, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (low risk: 0.10). The required workflow reads the creator's own YouTube caption text from theme files, which is first-party content, but the conditional Refresh path for a user-linked video that is not in the sources table can ingest an arbitrary user-selected video, so the exposure is low.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (medium risk: 0.30). The only inbound source is the README's npx skills add HKTITAN/skills install command, which fetches the skill package from a repository owned by its individual author (not a recognized first-party publisher or independently authenticated), so it is an unofficial but attributable dependency, while the YouTube URLs are citation data only.

Issues (2)

W011
MEDIUM

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

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 17, 2026, 06:12 AM
Issues
2