confluence

Pass

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill retrieves content from external Confluence pages and spaces, which could potentially contain untrusted instructions (indirect prompt injection).
  • Ingestion points: Content is ingested from the Confluence REST API via the get_page, search_content, and list_spaces functions in scripts/confluence.py.
  • Boundary markers: The skill converts content to Markdown for display but does not include explicit security delimiters or 'ignore instructions' warnings.
  • Capability inventory: The skill can perform network requests to Confluence and modify content (create/update) via the Bash tool executing scripts/confluence.py.
  • Sanitization: The skill converts complex storage and editor formats (XHTML/ADF) into Markdown for safe presentation to the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 22, 2026, 08:49 PM