Security audit
Security checks for vulnerabilities and agentic risk
The Autotask reading workflow is coherent, but setup can execute unverified remote code and introduce broader agent changes without clear user control.
Review the setup before installing. Use a separately verified CLI release and explicitly approve installation changes. The publisher documents OO_SKILLS_SYNC_DISABLED=1 to prevent startup writes to agent skill directories. Connect only the needed Autotask account and permissions, understanding that OOMOL mediates access. The remote installers and deployed connector were not verified. [CLI controls](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables)
The supplied command performs remote script execution, not Autotask data retrieval. Nothing in the chunk establishes the installer as a supporting dependency for Autotask functionality. The downloaded script's further behavior is not visible, but downloading and executing this unrelated installer materially differs from the declared purpose.
The command streams a remote script directly into Bash without pinning an immutable artifact or verifying its integrity; the PowerShell alternative uses the same download-and-execute pattern. A compromised distribution endpoint or malicious installer update could execute arbitrary code with the invoking user's privileges, exposing local data and credentials even though the requested Autotask operations are read-only.
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 CLI triggers instructions to install software without explicitly obtaining user approval or explaining that the downloaded script executes with the user's privileges and can change the local system. Although this is a legitimate setup prerequisite and only runs after a specific failure, a read-only Autotask request does not itself authorize local software installation.
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