backend-development-feature-development

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by interpolating user-provided feature descriptions directly into subagent task prompts. \n- Ingestion points: The $ARGUMENTS placeholder in SKILL.md is used across all phases to define the feature for subagents.\n- Boundary markers: No delimiters or protective instructions are used to isolate the user-provided arguments from the subagent instructions, increasing the risk of the agent following instructions embedded in the feature request.\n- Capability inventory: The workflow invokes subagents with high-privilege capabilities, including backend implementation, data pipeline engineering, and CI/CD deployment configuration.\n- Sanitization: The skill lacks validation, filtering, or escaping for user-supplied content before it is processed by the LLM subagents.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 03:02 AM
Security Audit — agent-trust-hub — backend-development-feature-development