Skills
skills/nishilbhave/codeprobe/codeprobe-code-smells/Gen Agent Trust Hub

codeprobe-code-smells

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to use the Bash tool for performing complex search and analysis tasks across the project codebase.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it processes untrusted project files and utilizes terminal-based tools. Ingestion points: Project source code is read using Read, Grep, and Glob tools, and configuration is loaded from .codeprobe-config.json. Boundary markers: There are no instructions to differentiate between the code being analyzed and potential instructions embedded in that code. Capability inventory: The skill uses Bash, Read, Grep, and Glob. Sanitization: No input validation or content filtering is implemented for the analyzed files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 05:31 AM