Security audit
Security checks for vulnerabilities and agentic risk
The OneDesk functions fit their purpose, but setup runs unverified downloaded code and leaves broader changes to agent skills undisclosed.
Review the setup before installing. Use a separately verified CLI release and require approval before local installation changes. Consider whether OOMOL should mediate your OneDesk access. Upstream documents OO_SKILLS_SYNC_DISABLED=1 to prevent startup skill synchronization in its [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables). The remote installer contents and exact installed release remain unverified.
The supplied code performs remote installer execution, not OneDesk searching or reading. Although installing a dependency can be a supporting implementation detail, nothing supplied establishes this installer's relationship to the declared OneDesk functionality. The downloaded script's contents and further effects are not shown.
Piping a live HTTPS download directly into Bash executes the endpoint's current contents without release pinning, signature verification, or an opportunity to inspect the script. Compromise of the distribution endpoint could yield arbitrary code execution with the invoking user's permissions; the PowerShell example has the same weakness. The documented vendor relationship and missing-CLI trigger make this a plausible setup workflow, not evidence of malicious intent, but do not eliminate the supply-chain risk.
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
When the CLI is missing, the skill directs the agent to execute a remote installer without first explaining the local system changes or obtaining installation-specific approval. A request to read OneDesk data does not inherently authorize installing software, although the conditional setup trigger limits exposure.
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