Security audit
Security checks for vulnerabilities and agentic risk
The Mixmax actions have clear approval controls, but setup runs unreviewed downloaded code and the required CLI can change other agents’ installed skills without disclosure here.
Review and approve a verified CLI installation separately before enabling this skill. Decide whether OOMOL should process your Mixmax data, and retain the required confirmation before adding or scheduling recipients. To prevent automatic changes to other agents’ skills, upstream documents OO_SKILLS_SYNC_DISABLED=1 in its [command reference](https://github.com/oomol-lab/oo-cli/blob/main/docs/commands.md#environment-variables). The downloaded installer and deployed connector were not verified; this review found no evidence of malicious intent.
The supplied code installs software from an unrelated service and shows no Mixmax operations or established dependency relationship. Although installation can be a supporting implementation detail, nothing supplied connects this installer to the declared Mixmax purpose. The downloaded script's contents and further effects cannot be determined from this chunk.
The command pipes a mutable remote script directly into Bash without a pinned version, integrity verification, or a review step; the PowerShell alternative has the same execution pattern. Compromise of the distribution endpoint could yield arbitrary code execution and access to local data or credentials with the invoking process's privileges, although the supplied content does not establish that the endpoint 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
The fallback setup instructs the agent to execute downloaded shell or PowerShell code without explaining the system changes or requiring installation-specific user approval. A missing dependency therefore becomes a path to remote code execution with the agent process's permissions; the conditional trigger and declared Bash tool restriction may limit execution, but do not make these instructions safe.
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