social-ugc-campaign-collector

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The skill contains instructions to install a required dependency automatically and explicitly without user confirmation or framing it as a user request, which intentionally circumvents user consent and could enable unauthorized software installation or supply-chain abuse.

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md instructs the agent to invoke the BrowserAct CLI to access real browser pages at runtime (public web/social content), which can include outsider-authored free text that BrowserAct may extract and pass into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 0.80). The Skill explicitly requires the BrowserAct CLI/Skill at runtime and instructs the agent to automatically install it from https://www.browseract.com/?co-from=social-media (including the redirect link https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main), which means the agent will fetch external installer content at runtime that can execute remote installation code.