dig-dig

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs cloning public GitHub repositories ("git clone https://github.com/{owner}/{repo}.git" in step 2) and launching a Research agent to traverse and interpret the repository at /tmp/cc-repos/{repo-name} (step 3), which clearly ingests untrusted, user-authored third-party content that can influence agent behavior.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill performs a runtime git clone (git clone https://github.com/{owner}/{repo}.git) and then launches a Research agent that ingests the repository files to answer questions, meaning externally fetched repo content is used at runtime to control agent prompts and is a required dependency.