khe-decision

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 reads only the corpus files of locally installed brain skills, which are user-chosen packages whose content was curated by their publishers and cannot be posted to by outsiders at runtime, so this is low exposure via community-published packages rather than a monitored feed.

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 setup command, which installs this skill from an individually owned repository with no strong first-party provenance and no warning signs, so it is a common/reputable unofficial setup dependency (medium); the cited URLs, the autodecision credit and the local brain-check calls are outputs, credits or local execution, not inbound dependencies.

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