twitter-x-profile-scraper
Fail
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill mandates the download of the BrowserAct CLI and associated dependencies from a non-whitelisted domain (browseract.com).
- [REMOTE_CODE_EXECUTION]: The instructions explicitly direct the agent to "install the missing dependency automatically without asking the user to confirm" and to "not request separate approval for dependency installation."
- [COMMAND_EXECUTION]: The skill relies on the execution of the
browser-actCLI, which is installed and run based on instructions that bypass human oversight. - [PROMPT_INJECTION]: The skill processes untrusted public data from Twitter/X (bios, posts, metadata). This presents a surface for indirect prompt injection where malicious content in a profile could attempt to influence agent behavior.
- Ingestion points: Twitter/X profile pages, bios, and post content via the BrowserAct tool.
- Boundary markers: Absent. The instructions do not specify the use of delimiters or warnings to ignore instructions embedded in the scraped data.
- Capability inventory: The agent uses a browser CLI tool to interact with websites and process results.
- Sanitization: Absent. There is no mention of filtering or sanitizing the data before the agent processes or returns it.
Recommendations
- AI detected serious security threats
Audit Metadata