atlassian-jira-confluence

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides tools to retrieve content from external platforms (Jira and Confluence) which may contain untrusted data that could influence the agent's behavior.\n
  • Ingestion points: Data enters the agent's context through methods like jira.issue(), jira.jql(), and confluence.get_page_by_id(), as documented in the provided README.md and reference files.\n
  • Boundary markers: The code templates provided in the documentation do not include specific delimiters or warnings to ignore instructions that might be embedded in the retrieved data.\n
  • Capability inventory: The skill possesses significant capabilities, including creating and updating issues and pages (e.g., issue_create, update_page), and managing attachments, which could be abused if an injected instruction is followed.\n
  • Sanitization: No sanitization or filtering of external content is implemented in the client initialization or the sample workflows to mitigate the risk of embedded malicious instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 01:37 PM
Security Audit — agent-trust-hub — atlassian-jira-confluence