confluence-browser-fetch

Warn

Audited by Snyk on May 8, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). This skill explicitly opens arbitrary Confluence sites/URLs (via --site or user-supplied inputs) and fetches user-generated page content, rendered browser HTML, REST page JSON, and attachments (see SKILL.md and scripts/confluence-browser-fetch.js which save page.browser.html, page.json, attachments.json and download attachments), so untrusted third‑party content is ingested into the agent's wiki workflow and could contain instructions that influence later agent behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 8, 2026, 08:22 PM
Issues
1