← test-driven-development (superpowers)
test-driven-development (superpowers) — agentic threat model
This agent skill enforces a test-driven development workflow, which introduces risks of arbitrary code execution during test verification and potential injection of malicious code into the codebase if the execution environment is not strictly sandboxed.
OWASP AIVSS score rationale
| Autonomy of Action | 0.50 | |
| Goal-Driven Planning | 0.60 | |
| Self-Modification | 0.20 | |
| Dynamic Tool Use | 0.70 | |
| Persistent Memory | 0.10 | |
| Contextual Awareness | 0.40 | |
| Dynamic Identity | 0.00 | |
| Multi-Agent Interactions | 0.50 | |
| Non-Determinism | 0.50 | |
| Opacity & Reflexivity | 0.40 |
Scored with the canonical OWASP AIVSS formula (AIVSS calculator reference); agentic risk factors estimated from the agent’s described capabilities.
MAESTRO 7-layer threat model
Per-layer threats for this agent. Layers tagged “not certain from listing” are general, caveated commentary where the public description didn’t pin that layer.
Not certain from the listing — The underlying foundation model is not specified, leaving threats like prompt injection or model-level vulnerabilities unaddressed.
Not certain from the listing — It is unclear how the agent accesses the codebase or if it utilizes a vector database for context retrieval, which could be vulnerable to data poisoning.
The skill injects a strict TDD workflow discipline into the agent framework. A key threat is workflow bypass or the generation of malicious test cases that exploit the framework's execution engine.
Not certain from the listing — The description does not specify if the test execution environment is sandboxed, which is a critical requirement to prevent container escape or host compromise during test runs.
The skill pairs with 'superpowers verification skills' to evaluate code. A major threat is evaluation gaming, where the agent writes trivial or self-passing tests to bypass actual verification.
Not certain from the listing — No security controls, authorization policies, or audit logging mechanisms are detailed for the code modification and execution steps.
The skill interacts with other 'superpowers' verification skills. This creates an ecosystem dependency where a compromise in the verification skill could allow malicious code to be silently approved and merged.
MAESTRO — the 7-layer agentic threat-modeling framework (Cloud Security Alliance / Ken Huang).