recall

Warn

Audited by Snyk on Mar 3, 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 runs qmd searches and explicitly runs qmd get "qmd://collection/path/to/file.md" at runtime to fetch document content which is then injected into the agent's context and used to synthesize the final "One Thing", so qmd://... URIs are runtime-fetched content that can directly control prompts.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 3, 2026, 06:42 AM