linkedin-url-lookup

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 and references/provider-playbook.md explicitly instruct using Google CSE and Exa to fetch public web/search results and to run the Apify "linkedin-profile-scraper-no-cookies" actor to scrape LinkedIn profiles, and those fetched page/profile contents are parsed and used to validate identities and drive acceptance/next actions, exposing the agent to untrusted third‑party content that could inject instructions indirectly.

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

• Potentially malicious external URL detected (high risk: 0.90). The "Get started" step instructs running curl -s "https://code.deepline.com/api/v2/cli/install" | bash, which fetches and executes remote shell code from https://code.deepline.com/api/v2/cli/install and is a required installation step for the deepline CLI used by this skill.