webapp-testing
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The helper script
scripts/with_server.pyutilizessubprocess.Popenwithshell=Trueandsubprocess.runto execute commands provided via CLI arguments. This functionality is intended to support the management of development servers and test execution during automated web testing. - [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes content from external web applications.
- Ingestion points: Browser console logs (
examples/console_logging.py), page content (SKILL.md), and UI element text (examples/element_discovery.py) are ingested into the agent's context. - Boundary markers: Absent. There are no specific delimiters or instructions to treat ingested web data as untrusted.
- Capability inventory: The skill possesses shell command execution capabilities via
scripts/with_server.pyand file system write access in the examples. - Sanitization: No sanitization or validation is performed on content retrieved from web pages before processing.
Audit Metadata