sdd-verify

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill is designed to automatically detect and run build and test commands found in configuration files such as package.json, pyproject.toml, or openspec/config.yaml. This execution is the intended primary function for providing behavioral evidence of code correctness.\n- [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it ingests various local project files (specification scenarios, design documents, and task lists) to guide its logic and generate compliance reports.\n
  • Ingestion points: The skill reads contents from specs/, design.md, tasks.md, and openspec/config.yaml.\n
  • Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions embedded within these source files.\n
  • Capability inventory: The skill has high-privilege shell access to execute build and test commands.\n
  • Sanitization: No validation or sanitization steps are documented before processing the file content or incorporating it into the verification summary.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 12:23 AM
Security Audit — agent-trust-hub — sdd-verify