confluence-dc

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 Confluence pages and attachments from third‑party/user-generated sources (via confluence_getContent, confluence_searchContent and scripts/download_confluence.py), and its upload/update workflow (scripts/upload_confluence.py and the PARENT_RELATIONSHIP_GUIDE) directs the agent to read YAML frontmatter (e.g., parent.id) and act on it, so untrusted page content can materially influence automated tool actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill's MCP configuration and installation instructions invoke and rely on the remote package @compasify/confluence-dc (executed via "npx -y @compasify/confluence-dc"), which fetches and runs remote code at runtime — repository: https://github.com/compasify/confluence-dc.