rhdh-jira-sprint-report
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The workflow in
workflows/summarize-sprint.mdexecutes shell commands using theacliutility. It interpolates user-provided variables such asBOARD_ID,SPRINT_ID, andTEAM_IDdirectly into command strings (e.g.,acli jira board list-sprints --board BOARD_ID). If these inputs are not properly sanitized by the underlying platform, they could be exploited for command injection. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external Jira issues which could contain malicious instructions.
- Ingestion points: Fetches issue summaries, labels, and status fields via
acli jira workitem searchinworkflows/summarize-sprint.md. - Boundary markers: None identified in the workflow instructions to separate data from instructions.
- Capability inventory: The skill can execute shell commands (
acli) and perform local file writes (sprint-report-{team}-{sprint}-{YYYY-MM-DD}.md) as seen inworkflows/summarize-sprint.md. - Sanitization: No explicit sanitization or escaping of the Jira issue content is described before it is displayed to the user or written to a file.
Audit Metadata