webapp-testing
Warn
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- COMMAND_EXECUTION (MEDIUM): The script
scripts/with_server.pyusessubprocess.Popenwithshell=Trueto execute server commands. This allows for potential command injection if the strings provided to the--serverflag are not strictly validated. - PROMPT_INJECTION (LOW): The skill instructions explicitly tell the agent 'DO NOT read the source until you try running the script first', which discourages self-auditing and could be used to hide malicious logic in the helper scripts.
- INDIRECT_PROMPT_INJECTION (LOW): The skill is designed to interact with and extract content from web applications using Playwright. Evidence Chain: 1. Ingestion points:
page.content()and DOM interaction. 2. Boundary markers: Absent. 3. Capability inventory: Arbitrary shell execution viawith_server.py. 4. Sanitization: None. This creates a surface where malicious web content could influence the agent's actions.
Audit Metadata