tipkit

Warn

Audited by Snyk on Apr 15, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Potentially malicious external URL detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to fetch missing documentation at runtime from the sosumi.ai Markdown mirror (e.g. https://sosumi.ai/documentation/tipkit/tip), which would inject remote Markdown into the agent context and thus directly influence prompts/outputs.

Issues (1)

W012
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 15, 2026, 01:53 AM
Issues
1