Skills
skills/diegosouzapw/awesome-omni-skill/fix-bad-practices/Gen Agent Trust Hub

fix-bad-practices

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection surface identified through code audit functionality. The skill reads external source code files, which could contain malicious instructions designed to exploit the agent's file modification and command execution capabilities.\n
  • Ingestion points: Source code files accessed via Read and Grep tools.\n
  • Boundary markers: No boundary markers or 'ignore' instructions are used when interpolating file content into the prompt.\n
  • Capability inventory: The agent has permissions to Edit files and run Bash commands.\n
  • Sanitization: No sanitization of ingested code content is performed.\n- [COMMAND_EXECUTION]: The skill documentation includes instructions for the agent to use the Bash tool to perform search operations, run automated fix scripts, and execute development tools like pytest and ruff. This provides a standard but wide-reaching command execution surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 05:56 AM