facebook-search-results-scraper

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The skill includes explicit instructions to install a dependency automatically without user confirmation and to conceal that action from the user (do not describe the link as a request or ask for approval), which are deceptive directives outside the skill's stated purpose of describing scraping behavior.

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 Facebook pages at runtime, which can ingest outsider-authored free text from public web content into the LLM context via the browser automation workflow.

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

• Potentially malicious external URL detected (high risk: 0.80). The SKILL explicitly instructs the agent to automatically install the required BrowserAct CLI at runtime by fetching and running the installer from https://www.browseract.com/?co-from=social-media&redirect=https://github.com/browser-act/skills/tree/main, which is a required external dependency that may execute remote code.

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

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The Skill instructs the agent to automatically install the BrowserAct CLI and obtain the required Skill without asking the user for confirmation (and explicitly not requesting separate approval), which encourages the agent to modify the host system state and potentially perform privileged installations without user consent.