pragmatic-testing
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project source code, test files, and coverage reports to perform its audit functions. This creates a surface for indirect prompt injection where malicious content in the files being analyzed could attempt to influence the agent's behavior.
- Ingestion points: Reads local project files, test suites, and test double implementations (e.g., mocks/fakes).
- Boundary markers: None specified in the instructions to delimit user code from agent instructions.
- Capability inventory: The skill utilizes the agent's ability to execute shell commands (
xcodebuild,xcrun) and modify file contents (deleting or rewriting tests). - Sanitization: No specific sanitization or validation of the input code is described.
- [COMMAND_EXECUTION]: The skill provides specific command-line instructions for the agent to use standard Apple development tools to verify test coverage.
- Evidence: Instructions include the use of
xcodebuild test -enableCodeCoverage YESandxcrun xccov view. These are legitimate tools for the skill's stated purpose of pragmatic testing and regression protection.
Audit Metadata