agent-best-practices
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute local shell commands including
git logto analyze commit history and multiple subcommands of thelangwatchCLI (such astrace search,scenario list, andanalytics query) to retrieve performance metrics and configuration. This behavior is consistent with the skill's stated purpose of auditing agent development and uses the vendor's own command-line tools. - [EXTERNAL_DOWNLOADS]: The skill identifies a dependency on the
langwatchCLI tool and assumes its presence in the environment to perform its analytical tasks. - [DATA_EXPOSURE_AND_EXFILTRATION]: The skill reads the full codebase and git history to perform its audit. This is the primary function of the skill and is performed locally to gather context for providing engineering improvements.
Audit Metadata