openclaw-github-repo-commander

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to clone and audit target GitHub repositories and to search GitHub for competitor repos (e.g., "Clone the target repository" and "Search GitHub for similar repositories"), which exposes it to untrusted, user-generated third-party content that the agent reads and uses to drive audits and remediation decisions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly clones and runs scripts from a user-supplied GitHub repository at runtime (e.g., https://github.com/owner/my-repo), so fetched remote repo content (like scripts/repo-audit.sh) is executed and thus can directly control behavior.