github-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes explicit examples that place tokens directly on the command line (e.g., GH_TOKEN=ghp_xxx), commands that print tokens (gh auth token / --show-token), and examples piping/setting secrets as literal values, which would require the agent to handle or emit secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.80). This skill's SKILL.md shows using gh to fetch and act on public, user-generated GitHub content (e.g., gh api / gh api graphql queries, gh issue view --comments, gh gist view --raw, gh repo view, gh project item-list and subsequent gh project item-edit) — meaning the agent would ingest untrusted third-party webpages/comments/gists and use that content to drive further CLI/API actions.