qodo-pr-resolver

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches PR/MR comments from external git providers (see "Step 3: Get Qodo review comments" and resources/providers.md § Fetch Review Comments) and then instructs the agent to read and literally execute Qodo's agent prompts as code-change instructions (see "Step 6" and "Step 7"), so untrusted, user-generated third-party content can directly influence tool actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill fetches Qodo review comments at runtime via provider APIs (e.g. gh api repos/{owner}/{repo}/pulls//comments -> https://api.github.com/repos/{owner}/{repo}/pulls//comments) and then explicitly executes the fetched "agent prompt" instructions as direct fixes, meaning remote content controls the agent's behavior.