twitter-x-follower-list-scraper
Fail
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references a third-party installation URL ('https://www.browseract.com/') to fetch the 'browser-act' CLI and Skill dependencies.
- [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." This bypasses critical human-in-the-loop security controls for software execution.
- [COMMAND_EXECUTION]: The skill relies on the 'browser-act' CLI tool, which is executed at runtime to interact with browser pages based on user-provided input.
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it scrapes and processes untrusted data from Twitter/X profiles (names, bios, and descriptions).
- Ingestion points: Twitter/X follower profiles (bios, names, handles) as described in SKILL.md.
- Boundary markers: Absent; there are no instructions to the agent to treat scraped content as untrusted or to ignore embedded instructions.
- Capability inventory: The skill utilizes the 'browser-act' tool for live web interaction and suggests storing session data (cookies, IDs) in 'workspaces/'.
- Sanitization: Absent; the skill does not specify any validation or filtering for the data collected from external profiles.
Recommendations
- AI detected serious security threats
Audit Metadata