backend-development-feature-development
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill passes user-provided input from the
$ARGUMENTSvariable directly into the prompts of multiple sub-agents throughout the discovery, implementation, testing, and deployment phases. - Ingestion points: User-supplied feature descriptions via the
$ARGUMENTSparameter inSKILL.md. - Boundary markers: Absent; there are no delimiters or specific instructions for sub-agents to ignore potentially malicious commands embedded within the feature descriptions.
- Capability inventory: The workflow orchestrates agents with significant capabilities, including code implementation (
backend-architect), security auditing (security-auditor), and deployment pipeline configuration (deployment-engineer). - Sanitization: No input validation, escaping, or filtering is applied to the external content before it is processed by the agent pool.
Audit Metadata