Security audit
Security checks for vulnerabilities and agentic risk
The AgentQL workflow is coherent, but fallback setup executes unverified downloaded software without clear approval and can introduce broader persistent changes.
Review and approve CLI installation separately before allowing fallback setup. Understand that requests use OOMOL and that its CLI can install skills into other agent hosts. The publisher documents OO_SKILLS_SYNC_DISABLED=1 to disable startup skill synchronization in its [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables). The remote installers could not be inspected, so their exact system changes remain uncertain. Preserve the skill's confirmation requirements for writes.
The supplied command installs software by executing a remotely fetched script; it does not perform any visible AgentQL operation. Nothing in the supplied content establishes this installer as a supporting dependency for AgentQL, so its purpose and external resource are inconsistent with the declaration. The downloaded script's further behavior cannot be determined from this chunk.
The supplied chunk performs only a CLI login, rather than implementing AgentQL operations. Authentication could be a supporting implementation detail if tied to AgentQL, but the supplied content establishes no such relationship. The authentication destination and any subsequent behavior cannot be determined from this command alone.
The curl-to-bash pipeline executes the current contents of a remote installer without pinning or verifying the executable artifact. HTTPS protects transport but does not protect against a compromised distribution server or malicious installer update; this is the same underlying installation risk identified by SQP-2, not evidence that the OOMOL domain is malicious.
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
A missing dependency triggers instructions to download and immediately execute shell or PowerShell code without installation-specific approval or integrity verification. Although dependency setup is relevant to this skill, this expands a normal AgentQL request into local code execution and system changes; a compromised installer could execute arbitrary code with the invoking user's privileges.
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