atr-browser
Fail
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: HIGHDATA_EXFILTRATIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
- [DATA_EXFILTRATION]: The skill provides tools that can expose sensitive browser data to the agent's context or local system.
- The
evalcommand is explicitly documented inreferences/commands-reference.mdas a way to retrieve authentication tokens usingwindow.localStorage.getItem('token'). - Inspection commands like
html,text,snapshot, andaskreturn page content which may contain PII or session-specific information. - Commands like
screenshot --fileanddownload-imagessave data to the/tmp/directory, which could be accessible by other local processes. - [DYNAMIC_EXECUTION]: The
atr browser eval <script>command enables the execution of arbitrary JavaScript within the browser context. - This allows for complex, runtime-generated logic that can bypass standard interaction patterns and directly manipulate the DOM, cookies, or browser APIs.
- [INDIRECT_PROMPT_INJECTION]: The skill presents a large attack surface for indirect prompt injection because it processes untrusted data from the web and possesses high-impact interaction capabilities.
- Ingestion points: Untrusted data enters the agent context through
snapshot,html,text,ask, andclean-snapshotcommands. - Capability inventory: The skill allows the agent to
click,fillforms (potentially with credentials),navigateto new URLs, andevalJavaScript. - Boundary markers: The instructions lack explicit delimiters or warnings to treat ingested web content as untrusted data, increasing the risk that the agent will follow instructions embedded in web pages.
- Sanitization: There is no evidence of sanitization or filtering of external content before it is processed by the agent or the sub-agent used by the
askcommand. - [COMMAND_EXECUTION]: The skill uses the
Bash(atr browser:*)tool to manage the browser lifecycle and perform automation. - While the tool is scoped, the broad range of subcommands allows for deep control over the browser environment, including network inspection and console access.
- [CREDENTIALS_UNSAFE]: The documentation encourages the retrieval of secrets from the browser environment.
- Example usage in
references/commands-reference.mdshows how to useevalto access sensitive authentication tokens, which may lead to insecure handling of these credentials in the LLM context.
Recommendations
- AI detected serious security threats
Audit Metadata