interest-discovery

Warn

Audited by Snyk on Mar 3, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill's required workflow (Step 2: "WebFetch ツールで RSS を取得" and references/hatena-categories.md listing public Hatena Bookmark RSS URLs) fetches and parses public, user-generated content (titles/descriptions/tags/bookmark counts) and explicitly uses that content to score, select, and act on articles, so untrusted third-party content can materially influence the agent's decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 3, 2026, 04:31 AM