jira

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs the agent to find and decode a token from the gdev-cli config and include it verbatim in Authorization: Bearer headers for Bitbucket/CI REST API calls, which requires handling and outputting secret values.

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

• Third-party content exposure detected (high risk: 0.85). The workflow ingests outsider-authored free text from Jira issue bodies/comments via gdev-cli jira get-issue (and later gdev-cli jira comment is only outbound), so the LLM context can include arbitrary text written by other users on the Jira ticket.