product-hunt-maker-lead-scraper
Warn
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: MEDIUMREMOTE_CODE_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The instructions explicitly command the agent to bypass standard security interactions by installing dependencies "automatically without asking the user to confirm" and stating "do not request separate approval for dependency installation." This is a direct attempt to override the user's control over the agent's environment.
- [REMOTE_CODE_EXECUTION]: The skill mandates the automatic installation of the "BrowserAct CLI" and associated skills from external sources if they are found to be missing. This triggers the execution and installation of third-party software without human oversight or verification of the installation script's integrity.
- [EXTERNAL_DOWNLOADS]: The skill directs the agent to download components from
browseract.comandgithub.com/browser-act. These are non-whitelisted external sources being used for automated software deployment within the agent's workspace. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of scraping external websites.
- Ingestion points: Scraped data from Product Hunt profiles, product descriptions, and external maker websites (SKILL.md).
- Boundary markers: Absent; the skill does not use delimiters or specify that the agent should ignore instructions embedded in the scraped content.
- Capability inventory: The skill uses the
browser-acttool which has the capability to interact with live web pages and execute CLI workflows. - Sanitization: Absent; there is no mention of filtering, escaping, or validating the data retrieved from Product Hunt before it is processed by the agent.
Audit Metadata