The Agent Skills Directory

[COMMAND_EXECUTION] (SAFE): The script scripts/ts_diagnostic.py executes shell commands using subprocess.run. The commands are hardcoded strings calling standard development tools (node, npx, grep) on local project paths. No untrusted input is interpolated into these commands.\n- [DATA_EXFILTRATION] (SAFE): The script reads local configuration files (package.json, tsconfig.json) and scans source code in the src/ directory. This is consistent with its stated purpose of project diagnostics. No network operations or data exfiltration attempts were detected.\n- [REMOTE_CODE_EXECUTION] (SAFE): There are no patterns of downloading or executing remote code. All operations are performed locally using standard system tools.\n- [PROMPT_INJECTION] (SAFE): No instructions attempting to override agent behavior or bypass safety filters were found in any of the analyzed files.

typescript-expert