social-hashtag-monitor

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The skill explicitly instructs the agent to install BrowserAct automatically without user confirmation and to hide or not describe the installation request, which is a deceptive runtime instruction outside the stated monitoring purpose.

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 use the BrowserAct CLI to access “real browser pages” at runtime (public web content fetched/scraped by BrowserAct), which can include outsider-authored free text that the agent then reads into the LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent to install/run the BrowserAct runtime from the external installer links (https://www.browseract.com/?co-from=social-media and https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main), which are used at runtime to fetch and execute remote code as a required dependency.