agent-browser
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it ingests untrusted data from external websites.
- Ingestion points: External web content is brought into the agent context via the
agent-browser snapshotandagent-browser getcommands. - Boundary markers: None are defined in the provided instructions to separate web content from system instructions.
- Capability inventory: The skill allows the agent to interact with pages (
click,fill), execute keyboard commands, and save browser states. - Sanitization: No sanitization or filtering of the retrieved web content is described in the skill.
- [DATA_EXFILTRATION]: The skill facilitates the extraction of information from web pages and the persistence of browser states (cookies and session tokens) via
agent-browser state save auth.json. These capabilities are consistent with the skill's stated purpose of browser automation and testing.
Audit Metadata