confluence-jira

Pass

Audited by Gen Agent Trust Hub on May 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides legitimate cross-product integration functionality as described in its documentation, using standard Confluence XHTML storage formats and REST APIs.
  • [SAFE]: Credential management is handled through environment variables (JIRA_API_TOKEN, etc.) or explicit CLI flags, avoiding hardcoded secrets or unsafe storage practices.
  • [PROMPT_INJECTION]: The create-from-page functionality represents an indirect prompt injection surface as it ingests data from Confluence pages to populate JIRA issues.
  • Ingestion points: Confluence page titles and body text read by the create_jira_from_page.py script.
  • Boundary markers: None identified in the provided documentation.
  • Capability inventory: REST API write access to JIRA for issue creation and read access to Confluence.
  • Sanitization: The documentation does not specify explicit sanitization, though the data is mapped to descriptive fields (summary/description) rather than executable instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 3, 2026, 07:14 PM
Security Audit — agent-trust-hub — confluence-jira