universal-quality-gate

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it explicitly instructs the agent to prioritize instructions from repository-local files.
  • Ingestion points: Reads project-controlled CLAUDE.md files and source code files (SKILL.md).
  • Boundary markers: No explicit boundary markers or 'ignore' instructions are used when reading project-level configuration.
  • Capability inventory: The skill uses the Bash tool to execute shell commands for linting and formatting (scripts/run_quality_gate.py).
  • Sanitization: No input sanitization or validation of external instructions is present in the wrapper script.
  • [COMMAND_EXECUTION]: The skill triggers the execution of various CLI tools based on the presence of marker files in the project. While these are common developer tools, this represents a potential surface for command injection if a project contains maliciously crafted configuration files that influence linter behavior or paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 03:15 AM
Security Audit — agent-trust-hub — universal-quality-gate