create-ticket

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes platform-specific command examples (notably the Jira curl using Basic auth with email:api-token) and instructs the agent to produce filing commands, which can require embedding API tokens/credentials verbatim in generated commands/outputs, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.70). The skill's workflow explicitly tells the agent to "Check for existing related issues" using commands like gh issue list --search and to "look at recent issues to match team conventions," which requires fetching and interpreting GitHub/GitLab issue content (user-generated, potentially public) as part of its ticket-creation logic, so untrusted third-party content can influence its actions.