Security audit
Security checks for vulnerabilities and agentic risk
The Jam export workflow is reasonable, but its setup can automatically execute unverified remote code and introduce broader changes to agent skills.
Review and preinstall a vetted CLI release before use, and review its automatic skill synchronization settings. Connect Jam with the minimum necessary permissions and consider that exported data passes through OOMOL. The bundled skill was fully inspected, but the external installer and installed runtime remain unverified.
The supplied command performs remote software installation, not Jam data retrieval. Nothing in the provided chunk establishes that this installation supports the declared Jam functionality. The downloaded script's contents are unavailable, so its further effects cannot be determined.
The setup command downloads mutable remote content and immediately executes it with the agent process's local privileges, without verifying a pinned version, signature, or trusted digest. Compromise of the installation endpoint or its distribution infrastructure could therefore expose local files and credentials or alter the environment; the missing-CLI condition limits exposure but does not make execution safe.
oo: command not found — install the oo CLI (other platforms: https://cli.oomol.com/install-guide.md):
curl -fsSL https://cli.oomol.com/install.sh | bash # macOS / Linux
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
- **`OOMOL_INSUFFICIENT_CREDIT`** — OOMOL billing stop. Recharge at `https://console.oomol.com/billing/token-recharge` before retrying.
- **HTTP 402 without `OOMOL_INSUFFICIENT_CREDIT`** — the third-party account itself has no active plan or credit. Report the provider error message as is; do not ask the user to recharge OOMOL.
## Resources