typescriptMITTrust: scannedUsed 3×

Command execution plan

A helper that flags shell commands requiring approval by matching risky patterns like deploy, rm, sudo, and curl-pipe; purely analytical with no execution.

Untrusted input — what to verify before you trust it

Outbound fetch helpers often lack SSRF guards, timeouts and redirect limits — the difference between a helper and an internal-network exfil vector. Confirm this card blocks internal addresses and bounds redirects and timeouts.

Preview

3 lines
// aperçu protégé · typescript · 3 lignes

3 more lines are delivered on retrieval, with the full verified card and its proof receipt.

What you get on retrieval

  • · The complete verified implementation, written to bytes by the MCP tool (near-zero output tokens).
  • · A proof receipt: source provenance, review status, license state and estimated savings.
  • · Revocation coverage — if a security fix lands on this primitive, retrievers are notified.
← Back to the full catalogue