jira-epic
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [PROMPT_INJECTION] (LOW): The skill presents an indirect prompt injection surface (Category 8) as it processes user input into automated actions. Evidence: 1. Ingestion points: User-provided feature descriptions and requirements are interpolated into the epic template. 2. Boundary markers: Absent; the template does not use delimiters or instructions to ignore embedded commands. 3. Capability inventory: The skill creates, updates, and transitions issues in Jira via the Atlassian MCP. 4. Sanitization: Absent; input is converted to Jira Wiki markup but instructions are not filtered.
- [COMMAND_EXECUTION] (SAFE): The skill uses Jira MCP tools strictly for its defined purpose of issue management. No unauthorized system commands or shell executions were detected.
- [DATA_EXFILTRATION] (SAFE): No hardcoded credentials or unauthorized data transmission patterns were found. The skill operates within the user's Jira environment using provided parameters.
Audit Metadata