feature-development-workflow

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill consists solely of a Markdown file describing an orchestration workflow. There are no executable files, scripts, or configuration files that could run code directly.
  • [PROMPT_INJECTION]: The skill defines a command-based workflow (/add-feature) that ingests external data, creating an indirect prompt injection surface.
  • Ingestion points: Untrusted data enters the agent context via the <reqs> parameter in the /add-feature command variants.
  • Boundary markers: No specific delimiters or "ignore instructions" warnings are defined in the orchestration documentation to separate user requirements from agent logic.
  • Capability inventory: The workflow involves multiple agents (e.g., abp-developer, qa-engineer) which are described as having the capability to write to the file system (Domain, Application, EF Core layers) and generate tests.
  • Sanitization: There is no evidence of sanitization, validation, or escaping of the user-provided requirements before they are passed to the automated workflow stages.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 04:32 PM