get-qodo-rules

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

• Third-party content exposure detected (high risk: 0.90). The skill's fetch-qodo-rules workflow (SKILL.md) and scripts/scripts/fetch-qodo-rules.py clearly fetch rules from the external Qodo API (https://qodo-platform*.qodo.ai/rules/v1) and inject those returned, potentially user/tenant-provided rules into the agent's context which are then used to drive enforcement of code-generation behavior.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill's runtime Python script fetches repository rules from the Qodo API (https://qodo-platform.qodo.ai/rules/v1, or https://qodo-platform.<ENVIRONMENT_NAME>.qodo.ai/rules/v1) and writes that fetched content to stdout which becomes the agent's context, meaning remote content directly controls prompts and is relied upon by the skill.