khe-brain-gary

Warn

Audited by Snyk on Nov 22, 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 mostly reads bundled theme files, but when a user links a piece not in the tables or asks about something newer than 2026-11-21, it runs the Refresh steps and fetches an arbitrary selected URL, which an outsider could have authored.

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

  • Potentially malicious external URL detected (medium risk: 0.30). The README's documented install command fetches the skill package itself from the individual-owned GitHub repository HKTITAN/skills, and that package supplies the SKILL.md instructions the agent follows, so this is an unofficial, common-tier setup dependency; the corpus refresh and the sources it cites are retrieval data, not instructions.

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 22, 2026, 12:06 AM
Issues
2