file-crdb-issue

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to read issue template files in .github/ISSUE_TEMPLATE/ and query labels from the public cockroachdb/cockroach GitHub repository (Step 1 and Step 3), meaning it ingests public GitHub content that it must interpret to choose templates, labels, and compose/follow-up actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill instructs the agent to read issue templates from the CockroachDB repo (e.g., https://github.com/cockroachdb/cockroach/.github/ISSUE_TEMPLATE/bug_report.md), which would be fetched at runtime and directly control the agent's assembled issue prompts/structure, so this is a runtime external dependency that controls prompts.