jira

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill connects to external Jira instances via Membrane and its documented actions (e.g., "Get Issue", "Get Comments", "Search Issues (JQL)" in SKILL.md) fetch user-generated issue descriptions and comments that the agent is expected to read and which could materially influence subsequent tool use or decisions.