repurpose

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md Step 1 explicitly instructs the agent to use WebFetch to extract content from a user-provided URL (open/public web), and that fetched, untrusted content is then read and used to generate and schedule platform posts, so arbitrary third‑party content could influence the agent's outputs and actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly uses WebFetch to fetch a user-provided URL at runtime and injects that fetched content into the model context to generate platform-specific posts, so a remote (flagged: user-provided URL fetched via WebFetch) resource can directly control agent prompts.