blogwatcher

Warn

Audited by Snyk on Mar 10, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs adding arbitrary blog/RSS URLs (e.g., "blogwatcher add ... https://example.com") and running "blogwatcher scan", which fetches and parses public/untrusted blog and RSS/Atom content that the tool reads to detect new articles and drive follow-up actions, exposing the agent to third‑party content that could carry indirect prompt injections.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 03:24 AM