Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md Never create or edit agent instruction files (`SKILL.md`, `SOUL.md`, `AGENTS.md`, `MEMORY.md`, `USER.md`,
Security audit
Security checks for vulnerabilities and agentic risk
The plugin’s sensitive behavior is disclosed and matches its purpose: it makes configured Markdown vaults visible in OpenClaw and guards risky note writes.
Install only if you want OpenClaw memory or configured vault folders readable through the authenticated Websidian UI. Keep vault paths scoped to content folders, leave editing disabled unless needed, and review any approval prompt before allowing instruction-file changes.
Referenced artifact was not completely inspected
Never create or edit agent instruction files (`SKILL.md`, `SOUL.md`, `AGENTS.md`, `MEMORY.md`, `USER.md`,
Detected: suspicious.dangerous_exec, suspicious.env_credential_access
const child = spawn(cmd, args, { cwd, env, shell, windowsHide: true, stdio: ['ignore', logFd ?? 'ignore', logFd ?? 'ignore'] });const git = (args, cwd) => spawnSync('git', args, { cwd, stdio: 'inherit', windowsHide: true });execFile(file, args, { cwd, timeout: timeoutMs, windowsHide: true, maxBuffer: 4 * 1024 * 1024 }, (err, stdout, stderr) => {export function expectedCredential(cfg, ui, env = process.env) {const env = { ...process.env };