jira-plan
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from Jira tickets, creating a surface for indirect prompt injection.
- Ingestion points: External Jira ticket fields including Summary, Description, Acceptance Criteria (AC), and Steps to Reproduce are retrieved via Jira tools or user input (SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters (e.g., XML tags or triple quotes) or 'ignore embedded instructions' warnings when processing the retrieved ticket content.
- Capability inventory: The agent is instructed to perform repository inspections (file read), use task/planning tools, and potentially use Jira update tools (jira-cr, jira-bug) based on the plan output.
- Sanitization: There is no evidence of sanitization, filtering, or validation of the text content extracted from Jira tickets before it is used to formulate implementation steps.
Audit Metadata