jev-social-research

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

• Third-party content exposure detected (low risk: 0.10). The agent researches social posts and trends by browsing and fetching web pages and social feeds, which exposes it to outsider-authored free text on open platforms.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill references a remote GitHub repository locator (https://github.com/socai-io/jev-social/tree/v0.1.9) and instructs the agent to execute it using npx github:socai-io/jev-social#v0.1.9, which constitutes an unverified runtime external dependency from an unofficial third-party source.