test-and-break
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill is highly susceptible to indirect prompt injection because it navigates to external URLs to perform testing.
- Ingestion points:
agent-browser open [DEPLOYMENT_URL]reads content from untrusted external websites. - Boundary markers: No delimiters or instructions are provided to the agent to treat website content as data rather than instructions.
- Capability inventory: The skill uses
agent-browserto interact with pages and has the ability to write files to the localtasks/directory. - Sanitization: There is no sanitization or validation of the external content before it is processed by the agent.
- External Downloads (LOW): The skill requires the global installation of
agent-browservia npm. This package is not from a source explicitly listed in the trusted organizations list, though it is a requirement for the skill's primary function. - Command Execution (SAFE): The skill executes shell commands (
agent-browserandjq). These are standard for its intended purpose of automated QA and report generation.
Audit Metadata