get-leads-at-company

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly scrapes and ingests public LinkedIn content (see the apify_run_actor_sync steps using "apimaestro/linkedin-company-employees-scraper-no-cookies" and "apimaestro/linkedin-profile-posts" in SKILL.md) and then analyzes those user-generated posts to generate personalization signals and outbound messages, so untrusted third-party content is read and can materially influence agent behavior.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill's "Get started" instructions tell users to run curl -s "https://code.deepline.com/api/v2/cli/install" | bash, which fetches and immediately executes remote code and is the installer for the deepline CLI that the skill's commands rely on, so this is a high-confidence runtime/execution dependency.