adspower-antidetect-browser
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the AdsPower desktop application to be installed on the host system to provide its local API services.
- Evidence: The installation section in
SKILL.mddirects users to download the software from its official website to enable API access. - [COMMAND_EXECUTION]: The skill provides code snippets for programmatically controlling browser instances through popular automation libraries.
- Evidence:
SKILL.mdincludes implementation examples for Selenium, Puppeteer, and Playwright that connect to the browser via WebSocket and debug ports. - Context: These capabilities are standard for the skill's intended purpose of marketing automation.
- [INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface for indirect prompt injection by design, as it facilitates the retrieval and processing of content from external websites.
- Ingestion points: Data enters the agent context through automated browser navigation using commands like
driver.get()orpage.goto()inSKILL.md. - Boundary markers: The provided code snippets do not include explicit instructions or delimiters for the agent to distinguish between its instructions and the content retrieved from external web pages.
- Capability inventory: The skill provides comprehensive control over browser profiles, including fingerprint manipulation, cookie isolation, and account management.
- Sanitization: No specific filtering or sanitization of ingested web content is present in the provided implementation examples.
Audit Metadata