jira-refinement
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted content from Jira issues, creating a potential vector for indirect prompt injection.
- Ingestion points: Step 1 of the workflow involves reading existing Jira descriptions, comments, and project requirements.
- Boundary markers: No explicit boundary markers or delimiters are provided in the instructions for isolating external data.
- Capability inventory: The skill utilizes Jira tools to apply changes to issues.
- Sanitization: The skill mitigates risks by requiring explicit human approval for all changes and directing the agent to remove secrets and personal data.
Audit Metadata