testrail
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external TestRail instances (titles, preconditions, steps, results) and uses it to generate Playwright test files.
- Ingestion points: Data is fetched from TestRail via the
testrail_get_casesMCP tool as described in the 'Import Test Cases' capability inSKILL.md. - Boundary markers: The instructions do not specify any boundary markers or instructions to ignore embedded commands within the imported TestRail data.
- Capability inventory: The skill possesses the capability to write new files (test generation) and execute shell commands via
npx playwright test. - Sanitization: There is no evidence of sanitization or escaping logic for external content before it is interpolated into code templates.
- [COMMAND_EXECUTION]: The skill triggers shell command execution to run tests and process results.
- Evidence:
SKILL.mdcontains instructions to executenpx playwright test --reporter=json > test-results.jsonto gather data for TestRail updates.
Audit Metadata