Skills
skills/sickn33/antigravity-awesome-skills/full-stack-orchestration-full-stack-feature/Gen Agent Trust Hub

full-stack-orchestration-full-stack-feature

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. User-provided input via $ARGUMENTS is directly interpolated into prompts for multiple specialized subagents across four development phases without sanitization or boundary markers.
  • Ingestion points: The $ARGUMENTS variable is used in prompts throughout SKILL.md.
  • Boundary markers: Absent. No delimiters or instructions are used to separate user data from subagent instructions.
  • Capability inventory: Subagents invoked in SKILL.md have capabilities to generate code, write database migrations, and configure CI/CD infrastructure.
  • Sanitization: No evidence of input validation, escaping, or filtering for the $ARGUMENTS data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 02:09 PM