frog-cycle
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data through user specifications and existing project files, which are interpolated into subagent prompts.
- Ingestion points: User-provided behavior specifications in the
LISTENphase; test and implementation file contents in theCROAK,LEAP, andSHEDphases. - Boundary markers: Prompts use structural headers (e.g.,
## Your Mission,## Context) but lack explicit instructions to ignore instructions embedded within the variables. - Capability inventory: The skill has the ability to write to the file system (modifying test and implementation files) and execute shell commands to run tests.
- Sanitization: There is no evidence of sanitization or escaping of external content before it is interpolated into the prompts.
- [COMMAND_EXECUTION]: The skill executes various shell commands to manage the TDD cycle.
- Runs test runners including
npx vitest,npx jest,uv run pytest,cargo test, andgo testbased on environment detection. - Executes
gw ci --affected --fail-fast --diagnosefor full suite verification in theCHORUSphase. - Uses
shasumto verify test file immutability during phase transitions. - [DYNAMIC_EXECUTION]: The skill dynamically constructs prompts for subagents (
opusandsonnetmodels) and invokes them using anAgent()function to perform phase-specific tasks like test writing, implementation, and refactoring.
Audit Metadata