test-driven-development
Pass
Audited by Gen Agent Trust Hub on May 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as
npm testand a local Python scriptscripts/aegis-workspace.py. These operations are routine for software development tasks and are scoped to the local environment. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8). It processes external data such as source code, test files, and test output during the TDD cycle.
- Ingestion points: Reading project source code and test files (
SKILL.md). - Boundary markers: None explicitly defined to separate instructions from the code being tested.
- Capability inventory: The agent can execute shell commands (
npm,python) and write files to the project directory. - Sanitization: No specific sanitization or validation of the processed code files is mentioned.
Audit Metadata