jira-shadow-refinement
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill analyzes untrusted data from user-provided stories and external Jira tickets, creating a surface for indirect prompt injection.
- Ingestion points: External data enters the context via user input or by fetching Jira ticket content through the Atlassian MCP.
- Boundary markers: The instructions lack explicit boundary markers or delimiters to separate the ingested ticket data from the skill's own instructions.
- Capability inventory: The skill has the capability to modify external state by updating Jira tickets or generating sub-tasks.
- Sanitization: There is no logic present to sanitize or validate the content of the user stories or tickets before processing.
Audit Metadata