Security audit
Security checks for vulnerabilities and agentic risk
The TheHive workflow has sensible controls, but its automatic setup executes unpinned remote code and may introduce broader changes to agent skills.
Review setup before installing. Use a separately verified, version-pinned CLI installation and explicitly approve software installation. Review or disable its automatic skill synchronization; current documentation provides OO_SKILLS_SYNC_DISABLED. Connect a least-privilege TheHive account and consider whether its incident data may pass through OOMOL. No malicious behavior was established, but the remote installer and hosted connector were not inspected. [CLI controls](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables).
The supplied chunk performs remote installer execution rather than any visible TheHive 5 operation. Nothing in the chunk establishes this installer as a supporting dependency for the declared purpose. The downloaded script's contents and downstream effects are not provided, so no further behavior or malicious intent can be established.
Piping a mutable HTTPS download directly into bash executes remotely supplied code without a pinned version or independent integrity verification; the PowerShell alternative has the same underlying issue. Compromise of the distribution endpoint could lead to execution with the agent process's privileges, including access to local files and credentials, although the declared tool restriction may block this command.
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 missing-CLI fallback instructs the agent to execute a remote installer without explicitly obtaining approval for installing software or running third-party code. This can expose the host to arbitrary code if the installer source is compromised; the conditional fallback and declared Bash(oo *) tool restriction reduce exposure but do not make the installation instructions safe if broader execution is available.
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