address-ticket

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

• Third-party content exposure detected (medium risk: 0.30). The skill reads Jira tickets and attachments which are user-submitted content from an external project management tool.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill references an external GraphQL endpoint (https://tablecheck.atlassian.net/gateway/api/graphql) in step 4 to query Jira designs, which constitutes an unverifiable external runtime dependency with weak provenance.