confluence-browser-fetch
Warn
Audited by Snyk on May 19, 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). This skill explicitly launches a browser and fetches arbitrary Confluence pages, rendered browser HTML, storage/view HTML, and attachments from a user-specified Atlassian site (see scripts/confluence-browser-fetch.js: fetchText/fetchJson saving page.browser.html, page.view.html, attachments, and SKILL.md which instructs ingesting raw/confluence/... into an LLM wiki), meaning untrusted, user-generated wiki content is ingested at runtime and could influence subsequent agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata