pw-debug-test
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill dynamically constructs shell commands using input provided by the user. Specifically, in Step 2, it executes
npx playwright test -g "<exact test title>". If a user provides a test title containing shell metacharacters (such as;,|, or`), it could lead to arbitrary command execution within the agent's environment. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it reads and processes external, potentially untrusted data to perform its analysis. Attackers could place malicious instructions in test files or trigger specific error messages that are then interpreted by the agent.
- Ingestion points: Spec files (read during Step 1), terminal output (Step 2), and Playwright trace files including actions, console logs, and network requests (Step 3).
- Boundary markers: No specific delimiters or boundary warnings are used to isolate external content from the agent's internal instructions.
- Capability inventory: File system read access, shell command execution via
npx playwright,ls, andgrep. - Sanitization: The skill lacks explicit sanitization for user-provided test names or validation for the content of the trace files before they are processed by the agent.
Audit Metadata