tdd-guide
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from requirement files and coverage reports, which represents a potential surface for indirect prompt injection. * Ingestion points:
scripts/tdd.pyingests requirement JSON objects and coverage reports in LCOV, JSON, and XML formats. * Boundary markers: Absent; no delimiters are used to separate external data from the agent's instructions. * Capability inventory: The skill can write generated test files to the filesystem. * Sanitization: Absent; the skill does not perform natural language sanitization of inputs before they influence the agent's output. - [DYNAMIC_EXECUTION]: The entry point
scripts/tdd.pyperforms dynamic loading of sibling modules from the local filesystem. * Evidence: The_siblingfunction inscripts/tdd.pyusesimportlib.util.spec_from_file_locationandmodule_from_specto dynamically importcoverage_analyzer,format_detector,metrics_calculator, andtest_generator.
Audit Metadata