ai-context-file-improver
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: No instructions attempting to bypass safety filters or override agent behavior were found. The skill focuses on legitimate configuration auditing.
- [DATA_EXFILTRATION]: The skill access is restricted to repository-level context files. It explicitly instructs the agent to avoid global user configuration files and contains no network exfiltration logic.
- [COMMAND_EXECUTION]: Discovery logic uses standard system utilities (ripgrep, find, PowerShell) to locate files within the project scope. These are benign and appropriate for the skill's purpose.
- [REMOTE_CODE_EXECUTION]: The skill does not download or execute scripts from remote sources. All logic is self-contained and focuses on text-based auditing.
Audit Metadata