jira-ticket-creator
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data sources, such as meeting notes, user stories, and free-text lists, to automate the creation of Jira tickets. This ingestion of external content creates a surface for indirect prompt injection where malicious instructions could be embedded in the notes to manipulate the ticket fields or the agent's behavior.
- Ingestion points: The skill reads and parses meeting action items, spec files, and free-text lists provided by the user or external documents (SKILL.md).
- Boundary markers: No specific technical delimiters are defined for the input data, but the workflow includes a required manual confirmation step.
- Capability inventory: The agent has the capability to write data to the Jira REST API to create tasks, stories, and bugs.
- Sanitization: The skill mitigates risks by requiring the user to review, edit, and approve a confirmation table before any tickets are actually created.
Audit Metadata