qt-cpp-review

Pass

Audited by Gen Agent Trust Hub on Apr 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a bundled Python script (references/lint-scripts/qt_review_lint.py) to perform deterministic code linting. The script is included in the skill package and operates locally without network access.
  • [DATA_EXFILTRATION]: The skill is designed to be read-only. It accesses local source files and git diffs to provide feedback. There is no evidence of data being transmitted to external endpoints or unauthorized file access.
  • [PROMPT_INJECTION]: As a code review tool, the skill processes untrusted source code provided by the user. This creates a surface for indirect prompt injection (e.g., instructions hidden in code comments), but the skill lacks high-privilege capabilities (like file writing or network access) that could be leveraged for an attack.
  • [REMOTE_CODE_EXECUTION]: No patterns of downloading or executing code from remote sources were found. All execution is limited to the provided linter script and standard platform tools like git.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 17, 2026, 04:29 AM