atlassian-reader
Warn
Audited by Snyk on Feb 24, 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). The skill explicitly fetches and ingests user-generated content from Atlassian Cloud (api.atlassian.com) — e.g., Jira issues/comments (Section 3 and 4) and Confluence pages (Section 6) — and directs the agent to read/convert that HTML/ADF content and take follow-up actions (like additional JQL searches), so untrusted third‑party content can influence behavior.
Audit Metadata