testrail

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted test data from TestRail (titles, preconditions, steps, and expected results) which is then used to generate executable Playwright tests. \n
  • Ingestion points: Data enters the context via the testrail_get_cases MCP tool (SKILL.md). \n
  • Boundary markers: The skill does not implement delimiters or instructions to prevent the agent from obeying potentially malicious instructions embedded in the TestRail data. \n
  • Capability inventory: The skill writes test files to the local system and executes them using npx playwright test. \n
  • Sanitization: No explicit sanitization or validation of the fetched TestRail content is described before interpolation into code templates. \n- [DYNAMIC_EXECUTION]: The skill programmatically generates Playwright scripts using templates populated with external data and subsequently runs them, which is a potential risk if the source content is malicious. \n- [COMMAND_EXECUTION]: The skill executes shell commands such as npx playwright test to run tests and capture output in JSON format. \n- [EXTERNAL_DOWNLOADS]: The skill uses npx to execute Playwright, which involves fetching software packages from the public npm registry.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 03:48 AM
Security Audit — agent-trust-hub — testrail