generate
Warn
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands via 'npx playwright test' to verify the scripts it generates (SKILL.md, Step 7). This runs code created during the session on the host environment.
- [REMOTE_CODE_EXECUTION]: The skill generates test files (.spec.ts/.spec.js) using LLM-generated logic derived from user input and codebase files, and subsequently executes them. This is a form of dynamic execution where the logic originates from potentially untrusted sources (Step 4, 7 in SKILL.md).
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting and processing untrusted data from the local codebase and user arguments without sufficient sanitization or boundary markers.
- Ingestion points: The skill reads user input from '$ARGUMENTS' and scans project files including 'playwright.config.ts', component source code, and existing tests (SKILL.md, Step 2).
- Boundary markers: No specific delimiters or instructions are used to treat the content of files as data rather than instructions.
- Capability inventory: The skill possesses the ability to write multiple files to the filesystem and execute shell commands (SKILL.md, Steps 4, 6, 7).
- Sanitization: There is no evidence of filtering or validation for the content retrieved from codebase files before it is used to generate executable code.
Audit Metadata