gh-cli

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md and referenced docs (e.g., "Step 1: Fetch directory structures" in SKILL.md and references/remote-analysis.md) instruct the agent to run gh api against arbitrary OWNER/REPO/contents paths on GitHub to fetch public, user-generated repository files, which the agent is expected to read and use to drive comparisons and decisions.