testrail
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
npx playwright testto run local tests and generate a JSON report. This is the primary intended function of the skill for test synchronization. - [INDIRECT_PROMPT_INJECTION]: The skill fetches test cases from an external source (TestRail) and processes their content to generate code or update statuses.
- Ingestion points: Data entering through the
testrail_get_casesMCP tool. - Boundary markers: Absent; instructions do not specify delimiters to separate untrusted TestRail content from instructions.
- Capability inventory: Shell command execution (
npx), file writing (Playwright test generation), and multiple MCP tool calls for data modification. - Sanitization: Absent; the skill is instructed to map preconditions and steps directly to code templates.
- [CREDENTIALS_UNSAFE]: The skill correctly instructs the user to configure sensitive information such as
TESTRAIL_API_KEYthrough environment variables rather than hardcoding them, adhering to secure development practices.
Audit Metadata