fix
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from user arguments including test file paths and descriptions, which are then interpolated into shell commands. This creates a potential surface for indirect prompt injection. Ingestion points: Arguments provided in SKILL.md. Boundary markers: Not present. Capability inventory: Execution of shell commands via npx playwright test in SKILL.md. Sanitization: No input validation or escaping logic found.
- [COMMAND_EXECUTION]: The skill executes npx playwright test commands. While this is the primary function, it grants the agent the ability to run code defined in the test files.
Audit Metadata