Security audit
Security checks for vulnerabilities and agentic risk
The TMDB features fit the stated purpose, but setup can execute unverified downloaded code without a clear user approval step.
Review and approve CLI installation separately, using a verified version. Consider disabling its managed-skill synchronization if you only want TMDB functionality; the [CLI reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md) documents OO_SKILLS_SYNC_DISABLED. Your TMDB requests and account connection use OOMOL. No malicious payload was established, but the downloaded installer could not be inspected.
The supplied command performs remote script execution and contains no TMDB search or read operation. Nothing in the supplied chunk establishes that this installer supports TMDB functionality, so its behavior is materially different from the declared purpose. The downloaded script's contents and further effects are not visible.
The supplied command performs a login operation rather than the declared TMDB search and reading functions. Authentication can be a supporting implementation detail, but the snippet provides no connection between oo and TMDB and contains no TMDB functionality.
The command pipes an unpinned HTTPS response directly into bash without verifying the downloaded artifact. A compromised installation endpoint or delivery infrastructure could therefore run attacker-controlled code with the agent's permissions; HTTPS alone does not establish installer integrity, and this is the same underlying installation risk noted in SQP-2.
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
The setup fallback instructs the agent to execute remotely downloaded shell or PowerShell scripts without an explicit approval checkpoint or artifact verification. If the installer source is compromised, it could execute arbitrary code with the agent's local permissions; triggering installation only when the CLI is missing reduces exposure but does not remove this risk.
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