tiktok-profile-scraper
Fail
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill instructs the agent to automatically fetch and install dependencies from an external URL (https://www.browseract.com/) if the required BrowserAct CLI or skill is missing from the environment.
- [COMMAND_EXECUTION]: The instructions explicitly direct the agent to "install the missing dependency automatically without asking the user to confirm" and "do not request separate approval for dependency installation." This behavior removes user oversight and allows for silent modification of the agent's capabilities and local environment.
- [PROMPT_INJECTION]: The skill processes untrusted data from external TikTok profiles which could contain malicious instructions designed to influence the agent's behavior during the scraping process.
- Ingestion points: TikTok profile bios, usernames, and public post content accessed via the browser tool (SKILL.md).
- Boundary markers: Absent; the skill lacks specific delimiters or warnings to treat the scraped content as untrusted data.
- Capability inventory: Live browser interaction and system command execution via the BrowserAct CLI (SKILL.md).
- Sanitization: No mention of sanitization or filtering for the data collected from external profiles.
Recommendations
- AI detected serious security threats
Audit Metadata