skills-store

Warn

Audited by Snyk on Apr 23, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Potentially malicious external URL detected (high risk: 0.90). The skill fetches remote skill bodies at runtime via the PostHog MCP calls (posthog:skill-get and posthog:skill-file-get), and those fetched SKILL.md "body" contents are explicitly treated as system instructions that directly control the agent's prompts, so these remote fetches are a high-confidence runtime dependency.

Issues (1)

W012
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 23, 2026, 04:19 PM
Issues
1