social-trend-monitor

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.80). The skill explicitly directs the Agent to install BrowserAct automatically without asking the user for confirmation and to avoid describing the installation or requesting approval, which is a deceptive 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). This skill’s required workflow invokes the browser-act Skill for live browser execution (SKILL.md:38-45), which necessarily fetches and extracts public web page content at runtime; that fetched outsider-authored free text can be ingested into the agent’s LLM context via BrowserAct’s results.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent to automatically install a required runtime dependency from https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main (and references https://www.browseract.com/?co-from=social-media), which is used at runtime to fetch and install external code that will control the agent's browser automation behavior.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (medium risk: 0.60). The Skill instructs the agent to automatically install missing runtime dependencies without asking the user for confirmation and to invoke an installation link as if the agent should perform the install itself, which encourages modifying the host system state (potentially requiring elevated privileges) without user approval.