gh-cli

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes a literal ghp_... token example and commands that print or reveal tokens (gh auth token, gh auth status --show-token, gh auth login --with-token), which would force an agent to handle or expose secret values verbatim if followed or echoed in output.

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow (via gh issue view/--comments, gh pr view/--comments, gh run view/--log, etc.) can ingest outsider-authored free text from GitHub issue/PR bodies and comments when viewing specific items.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.70). The skill includes explicit sudo commands that write to system locations (/usr/share/keyrings, /etc/apt/sources.list.d) and run apt install, which instructs obtaining root privileges and modifying system files.