code-ollama: `grep_search` Command Injection via Unescaped `$()` Shell Substitution (CWE-78)

## `grep_search` Command Injection via Unescaped `$()` Shell Substitution (CWE-78) ### Summary The `grep_search` tool in `code-ollama` constructs a shell command string by interpolating attacker-controlled `pattern` and `path` arguments, then executes it via `child_process.exec()`. The sanitization only escapes backslashes and double-quote characters, leaving `$()` command substitution and backtick expansion fully intact. A malicious or compromised Ollama server can therefore inject and execute arbitrary OS commands with the privileges of the local user running `code-ollama`. Because `grep_search` is classified as a read-only tool, it auto-executes in Plan mode without any user approval prompt, making this a no-interaction-required exploitation path. Severity is **High (CVSS 7.8)**. ### Details **Vulnerable sink — `src/utils/tools/filesystem/grep.ts:58-66`** ```ts const escapedPattern = searchPattern .replace(/\\/g, '\\\\') .replace(/"/g, '\\"'); const escapedDirPath = dirPath.replace(/\\/g, '\\\\').replace(/"/g, '\\"'); const { stdout } = await execShell( `rg --line-number --no-heading --smart-case "${escapedPattern}" "${escapedDirPath}"`, ); ``` Only `\` and `"` are neutralized. The shell metacharacter sequence `$()` (and backtick-style `` ` `` substitution) is passed through unmodified. The resulting string is passed to `execShell()` (`src/utils/tools/shell.ts:46-49`), which calls `exec` — the promisified `child_process.exec` defined at `src/utils/node.ts:1-4` — causing `/