pr-threads-resolve

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow in SKILL.md explicitly fetches and displays PR review threads from GitHub (e.g., via "gh pr-review threads list" / "review view" commands), which are user-generated/untrusted comments that the agent reads and uses to decide which threads to resolve, enabling indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill requires installing and running the GitHub CLI extension agynio/gh-pr-review via "gh extension install agynio/gh-pr-review" which will fetch and execute remote code from the GitHub repository (https://github.com/agynio/gh-pr-review) at runtime and is a required dependency for the skill's commands.