atlassian-admin

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing external administrative requests.
  • Ingestion points: The skill ingests untrusted data from user access requests, offboarding requests, and integration requirements defined in the 'User Provisioning', 'User Deprovisioning', and 'Integration Setup' workflows in SKILL.md.
  • Boundary markers: There are no explicit boundary markers or instructions defined to prevent the agent from following malicious commands embedded within these external requests.
  • Capability inventory: The agent possesses significant administrative capabilities through the Jira MCP and Confluence MCP integrations, including user creation, permission modification, and global system configuration.
  • Sanitization: The instructions do not specify any sanitization, validation, or filtering of the external request content before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 06:56 PM
Security Audit — agent-trust-hub — atlassian-admin