skills/fusengine/agents/code-quality/Gen Agent Trust Hub

code-quality

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • COMMAND_EXECUTION (SAFE): The skill uses grep for usage analysis and executes standard development linters (e.g., eslint, ruff, go vet). These commands are standard for software development and are used within their intended scope.
  • EXTERNAL_DOWNLOADS (SAFE): The skill references installation commands for well-known linters and formatters from established registries (npm, PyPI, Go, etc.). These are trusted tools in the development community and no suspicious third-party sources were identified.
  • PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection (Category 8) due to its core function of reading and processing untrusted codebase content.
  • Ingestion points: Source code files are read and interpreted via the explore-codebase agent and grep searches in Phases 1 and 3.
  • Boundary markers: Absent; the workflow does not implement specific delimiters or warnings to ignore instructions embedded in the analyzed code.
  • Capability inventory: The skill has capabilities to modify the file system (Phase 5), execute shell commands (Phases 4 and 6), and task subagents.
  • Sanitization: Absent; the skill relies on the AI agent's internal reasoning to identify violations and perform 'Precision Correction' without explicit input sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 08:17 AM