backend-patterns

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use standard shell commands (ls, cat, grep, rg) to inspect project files such as package.json, prisma/schema.prisma, and supabase/config.toml. This is a routine procedure for developer tools to understand the existing codebase.- [EXTERNAL_DOWNLOADS]: The provided code templates reference external dependencies from well-known and trusted registries (deno.land, esm.sh), which are standard for Supabase Edge Functions and related technologies.- [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection as it reads project-specific files that could potentially contain untrusted instructions.
  • Ingestion points: Project configuration files like package.json, prisma/schema.prisma, and supabase/config.toml (SKILL.md).
  • Boundary markers: No explicit markers or delimiters are used when reading these files.
  • Capability inventory: The agent can execute shell commands and access local files.
  • Sanitization: No explicit sanitization or validation of the ingested file contents is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 06:13 PM
Security Audit — agent-trust-hub — backend-patterns