orch-add-feature

Pass

Audited by Gen Agent Trust Hub on Sep 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill orchestrates the end-to-end building of new features based on user-supplied requirements. This creates a vulnerability surface where malicious instructions embedded in a feature request could potentially influence the research, planning, or implementation phases.
  • Ingestion points: User-provided descriptions of new features or capabilities to be implemented.
  • Boundary markers: None explicitly defined in this wrapper skill; the safety of the process depends on the boundary controls within the underlying orch-pipeline engine.
  • Capability inventory: Coordinates a pipeline involving research, task planning, TDD implementation (writing code), and repository commits.
  • Sanitization: The workflow incorporates manual 'Gates' for plan approval and pre-commit review, and includes logic to trigger a security-reviewer for sensitive features.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 12, 2026, 03:40 PM
Security Audit — agent-trust-hub — orch-add-feature