pr-mining-coordinator

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly runs commands that print and embed the GitHub token (e.g., security find-internet-password -s github.com -w and expects the token to be shown, and sets GITHUB_TOKEN via command substitution), which requires handling and outputting secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md and references (Phase 1/2 and references/mining-commands.md) explicitly instruct running gh / API-backed miner scripts (e.g., gh pr list and scripts/miner.py {repos} with a GitHub token) to fetch PR review comments from repositories — which are untrusted, user-generated third‑party content that the agent reads, interprets, and uses to generate rules and drive actions.