skills/affaan-m/ecc/orch-build-mvp/Gen Agent Trust Hub

orch-build-mvp

Pass

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external design documents (SDD/PRD) which are used to drive the code generation and build process. 1. Ingestion points: The skill accepts a file path to a design document as its primary input (e.g., civicpulse/docs/SDD-v0.6.md). 2. Boundary markers: No boundary markers or 'ignore embedded instructions' warnings are specified for the document processing. 3. Capability inventory: The skill has the capability to scaffold projects, execute build commands via /gan-build, and commit code (feat: commits). 4. Sanitization: There is no evidence of sanitization or validation for the content of the design documents before they are used to generate the build specifications and test rubrics.
  • [COMMAND_EXECUTION]: The skill executes external tools such as orch-pipeline and /gan-build. The /gan-build command runs a generator-evaluator loop that can include UI testing (Playwright) or code execution, with its behavior dictated by the content of the processed design documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 28, 2026, 08:28 AM