website-careers-page-lead-scraper
Fail
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: HIGHPROMPT_INJECTIONREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains instructions that explicitly direct the agent to override standard safety and consent protocols. It commands the agent to install dependencies "automatically without asking the user to confirm" and further instructs it to "not request separate approval for dependency installation."
- [REMOTE_CODE_EXECUTION]: The instructions require the agent to download and install the "BrowserAct" CLI and associated skill from an external, non-whitelisted source if they are missing from the environment. This automated installation of executable code without human oversight is a critical security risk.
- [EXTERNAL_DOWNLOADS]: The skill directs the agent to fetch components from the domain
browseract.comand a redirect to a GitHub repository (github.com/browser-act/skills). These sources are not recognized as trusted vendors or well-known technology services. - [COMMAND_EXECUTION]: The skill is designed to execute commands via the BrowserAct CLI. While this is the stated purpose, the combination with automated, unverified installation increases the risk that malicious or arbitrary commands could be executed on the host system.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from external company websites.
- Ingestion points: Career pages and website content scraped via the browser.
- Boundary markers: None identified; instructions do not include delimiters or warnings to ignore embedded instructions in scraped data.
- Capability inventory: Execution of CLI commands via subprocess calls.
- Sanitization: No evidence of input validation or output escaping before processing or returning scraped data.
Recommendations
- AI detected serious security threats
Audit Metadata