vibium-browser-automation
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to the way it processes external web content.
- Ingestion points: Untrusted data from web pages is ingested via the
browser_navigatetool and converted to text through screenshots processed byeasyocr, as detailed inreferences/easyocr-workflow.mdandreferences/limitations.md. - Boundary markers: The skill's instructions and examples do not include delimiters or specific instructions (e.g., "ignore embedded instructions") to prevent the agent from obeying malicious commands found within the extracted text.
- Capability inventory: The skill provides high-privilege interaction tools such as
browser_click,browser_type, andbrowser_navigate(defined inSKILL.md), which could be leveraged by an attacker who successfully injects instructions into the processed content. - Sanitization: There is no evidence of sanitization, escaping, or filtering of the OCR-extracted text before it is analyzed by the agent.
Audit Metadata