skills/udecode/better-convex/lfg/Gen Agent Trust Hub

lfg

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill acts as an orchestrator for internal engineering tools (slash commands) to manage workflows and browser testing.
  • [PROMPT_INJECTION]: No instructions aimed at overriding system prompts, bypassing safety protocols, or extracting system information were detected.
  • [DATA_EXFILTRATION]: The skill does not access sensitive local files (like SSH keys or environment variables) and contains no network-based exfiltration patterns.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides an interface for processing user-supplied feature descriptions through the $ARGUMENTS variable.
  • Ingestion points: User input from $ARGUMENTS is passed directly to the /workflows:plan command in SKILL.md.
  • Boundary markers: None present.
  • Capability inventory: The skill triggers engineering workflow commands and browser verification tools.
  • Sanitization: Input is processed as-is by the subsequent command without explicit sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 01:20 AM