tdd-orchestrator
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data, such as requirements and user stories, and use that data to orchestrate high-privilege development tasks like build system integration and CI pipeline design. This creates a surface where malicious instructions embedded in project documentation could influence the agent's actions.
- Ingestion points: The skill explicitly ingests "requirements and user stories" and "code changes" (SKILL.md).
- Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands in the ingested data.
- Capability inventory: The skill is capable of orchestrating build systems (Maven, Gradle, npm, Cargo, MSBuild), managing environment provisioning, and designing CI pipelines (SKILL.md).
- Sanitization: The instructions do not define any sanitization or validation protocols for the external input processed during orchestration.
- [SAFE]: No evidence of malicious obfuscation, credential harvesting, or unauthorized remote code execution patterns was found in the provided file. The instructions focus on established TDD best practices and multi-agent coordination.
Audit Metadata