test-driven-development
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute shell commands via the
terminaltool to perform the TDD cycle. - Evidence: Examples such as
pytest tests/test_feature.py::test_specific_behavior -vare used to verify test failure (RED) and success (GREEN). - [INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection because it ingests and executes content from external files in the project workspace.
- Ingestion points: The skill reads and processes files within the
tests/directory (e.g.,SKILL.mdinstructions for subagents). - Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat content from the workspace as untrusted data.
- Capability inventory: The skill assumes and utilizes
terminaltool access, which allows for shell execution. - Sanitization: No validation or sanitization of filenames or file content is performed prior to execution through the terminal tool.
Audit Metadata