Jira Orchestration Workflow
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where the agent ingests data from external Jira issues, including summaries and acceptance criteria, which are then used to drive code generation and deployment actions. This creates a surface for indirect prompt injection where an attacker could influence the agent's behavior by placing instructions in a Jira ticket.
- Ingestion points: Phase 1 (EXPLORE) fetches issue details, acceptance criteria, and linked issues from the Jira API.
- Boundary markers: None identified; instructions do not specify using delimiters or warnings to ignore embedded instructions in the ingested data.
- Capability inventory: The workflow grants the agent capabilities to perform file system writes (Phase 3: CODE), execute tests (Phase 4: TEST), and perform network/Git operations such as creating PRs and commits (Phase 6: COMMIT).
- Sanitization: The skill lacks explicit instructions for sanitizing or validating the content retrieved from Jira before it is processed by the agent.
Audit Metadata