rhdh-prepare-refinement
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Jira issues that may contain malicious instructions designed to alter the agent's behavior.
- Ingestion points: In
workflows/prepare-refinement.md(Step 4), the skill retrieves and parses summary, description, and comment fields from Jira work items. - Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the ingested Jira text.
- Capability inventory: The skill uses
aclifor Jira data retrieval andjqfor JSON processing. - Sanitization: No sanitization is performed on the data retrieved from Jira before it is analyzed and synthesized.
- [COMMAND_EXECUTION]: The workflow relies on local command execution to fetch data from Jira.
workflows/prepare-refinement.mdcontains several shell commands using theaclitool andjqto list sprints, search issues, and view work item details.
Audit Metadata