jira-issue-to-pr
Pass
Audited by Gen Agent Trust Hub on Jul 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing external data from Jira tickets and passing it to an AI agent.
- Ingestion points: The poller script
scripts/main.pyretrieves thesummaryanddescriptionfields from Jira issues via the Atlassian REST API. - Boundary markers: The Jira content is interpolated directly into the agent's prompt template in
scripts/main.pywithout using delimiters or explicit instructions to ignore embedded commands. - Capability inventory: The spawned agent has capabilities to perform file system modifications and network operations, including cloning repositories and pushing code to GitHub.
- Sanitization: No sanitization, validation, or filtering is performed on the content retrieved from Jira before it is processed by the agent.
Audit Metadata