captain-obvious

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local system commands including git and mypy using subprocess.run in Python and spawnSync in Node.js. These calls are used to verify that the repository has no uncommitted changes and to perform static type analysis on the source code.
  • [SAFE]: The skill modifies source code files by deleting or rewriting redundant test assertions. This is the primary stated purpose of the tool and is performed using deterministic AST parsing rather than opaque LLM generation.
  • [SAFE]: The skill follows security best practices by implementing a 'Git Guard' that refuses to modify files unless the working tree is clean, ensuring that users can easily undo any changes made by the skill.
  • [SAFE]: No network operations, credential harvesting, or obfuscated code patterns were detected. The skill operates entirely within the local filesystem and the project's established development environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 09:39 AM
Security Audit — agent-trust-hub — captain-obvious