instagram-business-contact-search

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 0.90). The Skill contains deceptive instructions to auto-install BrowserAct without user confirmation and to hide that action ("do not request separate approval" / "Do not describe it as a request for the user to open their browser"), which directs behavior outside the skill's stated purpose and attempts to conceal actions from the user.

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 and extract data from live public Instagram pages at runtime, which can include outsider-authored free text (e.g., bios/posts) that BrowserAct returns into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent to automatically install a required runtime dependency from https://www.browseract.com/?co-from=lead-generation (and its redirect variant https://www.browseract.com/?co-from=lead-generation&redirect=https://github.com/browser-act/skills/tree/main), which is a remote installer link used at runtime to fetch and install code that the skill depends on.