The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown text defining a persona and administrative workflows for Atlassian Cloud/Data Center management. There are no executable scripts or system configuration files included in the skill package.\n- [PROMPT_INJECTION]: No malicious patterns or attempts to override system safety guidelines were detected. Instructional markers like 'CRITICAL' and 'IMPORTANT' are used correctly within the context of business logic, such as auditing content during user offboarding.\n- [DATA_EXFILTRATION]: No hardcoded credentials, API keys, or sensitive file paths were found. The skill describes the management of API tokens as a standard administrative duty rather than an automated or malicious exfiltration mechanism.\n- [REMOTE_CODE_EXECUTION]: There are no commands for downloading external scripts, installing packages, or executing remote code. The mention of Atlassian Marketplace apps is purely descriptive of a workflow for manual evaluation and installation.

atlassian-admin