skills/knowlet/skills/code-reviewer/Gen Agent Trust Hub

code-reviewer

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill's core purpose is to process and analyze external source code and specification files, which creates an attack surface for indirect prompt injection. * Ingestion points: The script review.py accepts external file and directory paths via --file and --spec arguments. * Boundary markers: No delimiters or instructions to ignore embedded commands were found in the skill definitions. * Capability inventory: The skill has the ability to execute a local Python script (review.py) to perform analysis. * Sanitization: No sanitization or validation of the input file content is mentioned.
  • Command Execution (SAFE): The skill defines command-line execution for its own internal Python scripts. This is part of the skill's intended functionality and follows standard practices for local script execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:21 PM