khe-brain-harshit

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 answers from bundled reference files of Harshit's own posts, but the conditional Refresh step in SKILL.md can re-read his X/LinkedIn timeline, where outsider replies could be ingested.

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's own instructions from an individual-owned repository, so it is a common/reputable unofficial dependency (medium), while the X and LinkedIn links are cited data, not operational content.

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