capture-triage

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.70). The skill reads and classifies user-provided Markdown captures from the Inbox folder (ls /Users/.../Inbox/*.md) and explicitly extracts and preserves arbitrary source URLs (including x-bookmark tweet_url and other frontmatter or body URLs) — i.e., it ingests untrusted, third‑party/user-generated content as part of its workflow (and can spawn a research-swarm that would further investigate those sources).
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 06:09 AM