etsy-keyword-research
Fail
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill instructs the agent to automatically download and install the BrowserAct CLI and associated skill from an external URL (browseract.com) if they are not already present on the system.
- [COMMAND_EXECUTION]: There are explicit instructions for the agent to bypass user interaction for software installation. The text states that the agent should install missing dependencies "automatically without asking the user to confirm" and should "not request separate approval for dependency installation." This attempts to override the agent's safety protocols requiring user consent for potentially dangerous system operations.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and process external content from Etsy search results and product pages, which are controlled by third parties.
- Ingestion points: Capturing browser-visible page content and visible metadata (SKILL.md, Instruction 5).
- Boundary markers: No boundary markers or instructions to ignore embedded commands in the scraped data are present.
- Capability inventory: The skill uses the browser-act tool to interact with websites and return data to the agent.
- Sanitization: No mentions of sanitization, filtering, or validation of the ingested web content are provided.
Recommendations
- AI detected serious security threats
Audit Metadata