openspec-plus-tdd

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill defines a rigorous workflow for Test-Driven Development (TDD), focusing on an atomic Red-Green-Refactor cycle. It does not include any network operations, data exfiltration patterns, or unauthorized privileged commands.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon content from external project files, which represents a potential attack surface if those files contain malicious instructions.
  • Ingestion points: The agent reads tasks.md, spec.md, design.md, and project-specific guidelines such as AGENTS.md or CLAUDE.md to drive the TDD process.
  • Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions potentially embedded within these requirement or design files.
  • Capability inventory: The workflow requires the agent to write production code, create test files, and execute test suites based on the provided specifications.
  • Sanitization: The skill does not specify any sanitization, filtering, or validation steps for the content parsed from the markdown specification files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 01:15 AM
Security Audit — agent-trust-hub — openspec-plus-tdd