qa-manual-tests-to-code-coverage

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches manual test cases from the vendor's platform using npx check-tests pull and utilizes @testomatio/reporter from the npm registry.
  • [COMMAND_EXECUTION]: Executes shell commands including grep for data extraction and npx to run vendor-provided CLI tools for reporting and synchronization.
  • [COMMAND_EXECUTION]: Runs a bundled validation script scripts/check-coverage.mjs via node to verify the generated coverage mapping.
  • [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection (Category 8) as it processes external, potentially untrusted data.
  • Ingestion points: Processes manual test markdown files (.test.md) and the project's source code files (Step 1, Step 2, Step 3).
  • Boundary markers: Absent; the skill does not define specific delimiters or instructions to ignore potential commands embedded within the test cases or source code.
  • Capability inventory: The agent has the ability to execute shell commands (grep, npx, node) and write files to the repository (coverage.manual.yml, .gitignore).
  • Sanitization: Absent; content from the analyzed files is read and interpreted by the agent without prior filtering or sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 06:37 PM
Security Audit — agent-trust-hub — qa-manual-tests-to-code-coverage